SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
This report summarizes scanner evidence for NVlabs/Sana, a Python project with 9,246 GitHub stars. SynthScan examined 153,648 lines of code across 499 source files, recording 1932 pattern matches distributed across 22 syntactic categories. The legacy adjusted pattern signal is 19.7 (Elevated pattern signal); it is not an authorship estimate.
Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.
Use each vector to guide manual verification of the underlying findings.
Can maintainers explain intent, assumptions, and trade-offs? 975 finding(s).
Are imports declared and package/API names verified? 374 finding(s).
Are wrappers, guards, and repeated structures necessary? 1044 finding(s).
Which changes need focused human review? 1932 finding(s).
This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.
Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.
This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.
The scanner identified 1932 distinct pattern matches across 22 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.
Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | environment_setup.sh | 2 | # ----------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | environment_setup.sh | 13 | # ----------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | tools/metrics/sana_wm/eval_unified.py | 615 | # ============================================================================ | COMMENT |
| MEDIUM⚡ | tools/metrics/sana_wm/eval_unified.py | 617 | # ============================================================================ | COMMENT |
| MEDIUM⚡ | tools/metrics/sana_wm/eval_unified.py | 875 | # ============================================================================ | COMMENT |
| MEDIUM⚡ | tools/metrics/sana_wm/eval_unified.py | 877 | # ============================================================================ | COMMENT |
| MEDIUM⚡ | tools/metrics/sana_wm/eval_unified.py | 936 | # ============================================================================ | COMMENT |
| MEDIUM⚡ | tools/metrics/sana_wm/eval_unified.py | 938 | # ============================================================================ | COMMENT |
| MEDIUM | tools/metrics/sana_wm/eval_unified.py | 106 | # ============================================================================ | COMMENT |
| MEDIUM | tools/metrics/sana_wm/eval_unified.py | 108 | # ============================================================================ | COMMENT |
| MEDIUM | tools/metrics/sana_wm/eval_unified.py | 220 | # ============================================================================ | COMMENT |
| MEDIUM | tools/metrics/sana_wm/eval_unified.py | 222 | # ============================================================================ | COMMENT |
| MEDIUM | tools/metrics/sana_wm/eval_unified.py | 1046 | # ============================================================================ | COMMENT |
| MEDIUM | tools/metrics/sana_wm/eval_unified.py | 1048 | # ============================================================================ | COMMENT |
| MEDIUM | diffusion/post_training/rewards.py | 15 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/post_training/rewards.py | 17 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/post_training/rewards.py | 81 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/post_training/rewards.py | 83 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | diffusion/post_training/rewards.py | 107 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | diffusion/post_training/rewards.py | 109 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/post_training/rewards.py | 185 | # ========================================================================= | COMMENT |
| MEDIUM | diffusion/post_training/rewards.py | 187 | # ========================================================================= | COMMENT |
| MEDIUM | diffusion/post_training/rewards.py | 319 | # ========================================================================= | COMMENT |
| MEDIUM | diffusion/post_training/rewards.py | 321 | # ========================================================================= | COMMENT |
| MEDIUM | …post_training/diffusers_patch/pipeline_with_logprob.py | 32 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …post_training/diffusers_patch/pipeline_with_logprob.py | 34 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …post_training/diffusers_patch/pipeline_with_logprob.py | 197 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …post_training/diffusers_patch/pipeline_with_logprob.py | 199 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …post_training/diffusers_patch/pipeline_with_logprob.py | 346 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …post_training/diffusers_patch/pipeline_with_logprob.py | 348 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …usion/distributed/context_parallel/distributed_scan.py | 58 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …usion/distributed/context_parallel/distributed_scan.py | 60 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …usion/distributed/context_parallel/distributed_scan.py | 144 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …usion/distributed/context_parallel/distributed_scan.py | 146 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …usion/distributed/context_parallel/distributed_scan.py | 184 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …usion/distributed/context_parallel/distributed_scan.py | 186 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …usion/distributed/context_parallel/distributed_scan.py | 234 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …usion/distributed/context_parallel/distributed_scan.py | 236 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …usion/distributed/context_parallel/distributed_scan.py | 464 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | …usion/distributed/context_parallel/distributed_scan.py | 466 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 663 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 665 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 69 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 71 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 118 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 120 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 151 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 153 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 270 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 272 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 313 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 315 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 346 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 348 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | diffusion/utils/action_overlay.py | 43 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/utils/action_overlay.py | 45 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/utils/action_overlay.py | 121 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/utils/action_overlay.py | 123 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/model/edm_sample.py | 28 | # ---------------------------------------------------------------------------- | COMMENT |
| MEDIUM | diffusion/model/edm_sample.py | 83 | # ---------------------------------------------------------------------------- | COMMENT |
| 271 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | tools/convert_sana_wm_refiner_to_diffusers.py | 42 | CODE | |
| LOW | tools/metrics/sana_wm/eval_unified.py | 51 | CODE | |
| LOW | tools/metrics/sana_wm/pose_utils.py | 3 | CODE | |
| LOW | tools/metrics/sana_wm/aggregate_results.py | 20 | CODE | |
| LOW | tools/metrics/geneval/generation/diffusers_generate.py | 15 | CODE | |
| LOW | tools/metrics/pytorch-fid/src/pytorch_fid/inception.py | 7 | CODE | |
| LOW | tools/metrics/pytorch-fid/src/pytorch_fid/inception.py | 9 | CODE | |
| LOW | tools/controlnet/inference_controlnet.py | 37 | CODE | |
| LOW | tools/controlnet/inference_controlnet.py | 37 | CODE | |
| LOW | tools/convert_scripts/convert_sana_to_svdquant.py | 2 | CODE | |
| LOW | tools/convert_scripts/convert_sana_to_diffusers.py | 2 | CODE | |
| LOW | …ols/convert_scripts/convert_sana_video_to_diffusers.py | 2 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint_chunk.py | 36 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint.py | 31 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint.py | 35 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint.py | 38 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint.py | 47 | CODE | |
| LOW | app/app_sana_multithread.py | 17 | CODE | |
| LOW | app/sana_pipeline.py | 28 | CODE | |
| LOW | app/sana_pipeline.py | 28 | CODE | |
| LOW | app/sana_pipeline.py | 28 | CODE | |
| LOW | app/sana_pipeline.py | 28 | CODE | |
| LOW | app/sana_controlnet_pipeline.py | 31 | CODE | |
| LOW | app/sana_controlnet_pipeline.py | 31 | CODE | |
| LOW | app/sana_controlnet_pipeline.py | 31 | CODE | |
| LOW | app/sana_controlnet_pipeline.py | 31 | CODE | |
| LOW | app/sana_pipeline_inpaint.py | 20 | CODE | |
| LOW | app/sana_pipeline_inpaint.py | 31 | CODE | |
| LOW | app/sana_pipeline_inpaint.py | 31 | CODE | |
| LOW | app/sana_pipeline_inpaint.py | 31 | CODE | |
| LOW | app/sana_pipeline_inpaint.py | 31 | CODE | |
| LOW | app/sana_pipeline_inpaint.py | 41 | CODE | |
| LOW | app/safety_check.py | 19 | CODE | |
| LOW | app/safety_check.py | 21 | CODE | |
| LOW | app/safety_check.py | 21 | CODE | |
| LOW | app/app_sana_4bit.py | 21 | CODE | |
| LOW | app/app_sana.py | 17 | CODE | |
| LOW | app/app_sana.py | 32 | CODE | |
| LOW | app/sana_sprint_pipeline.py | 32 | CODE | |
| LOW | app/sana_sprint_pipeline.py | 32 | CODE | |
| LOW | app/app_sana_inpaint.py | 8 | CODE | |
| LOW | app/app_sana_sprint.py | 17 | CODE | |
| LOW | tests/test_fastvideo_dmd_sampler.py | 16 | CODE | |
| LOW | sana/tools/__init__.py | 1 | CODE | |
| LOW | sana/tools/__init__.py | 2 | CODE | |
| LOW | sana/tools/__init__.py | 2 | CODE | |
| LOW | diffusion/__init__.py | 3 | CODE | |
| LOW | diffusion/__init__.py | 4 | CODE | |
| LOW | diffusion/__init__.py | 5 | CODE | |
| LOW | diffusion/__init__.py | 5 | CODE | |
| LOW | diffusion/__init__.py | 5 | CODE | |
| LOW | diffusion/__init__.py | 6 | CODE | |
| LOW | diffusion/__init__.py | 7 | CODE | |
| LOW | diffusion/__init__.py | 8 | CODE | |
| LOW | diffusion/__init__.py | 9 | CODE | |
| LOW | diffusion/__init__.py | 10 | CODE | |
| LOW | diffusion/post_training/rewards.py | 5 | CODE | |
| LOW | diffusion/post_training/dataset/pickscore/prpocess.py | 3 | CODE | |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 31 | CODE | |
| LOW | …usion/distributed/context_parallel/distributed_scan.py | 23 | CODE | |
| 294 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | tools/convert_sana_wm_refiner_to_diffusers.py | 135 | def fuse_distilled_lora_inplace( | CODE |
| LOW | tools/convert_sana_wm_refiner_to_diffusers.py | 191 | def convert_connectors_to_diffusers(checkpoint: dict[str, object]) -> dict[str, object]: | CODE |
| LOW⚡ | tools/metrics/sana_wm/eval_unified.py | 620 | def _build_stripped_video_dir(video_dir: str, output_dir: str) -> str: | CODE |
| LOW⚡ | tools/metrics/sana_wm/eval_unified.py | 941 | def eval_temporal_degradation( | CODE |
| LOW | tools/metrics/sana_wm/eval_unified.py | 94 | def _resolve_vbench_info_path(vbench_module) -> str: | CODE |
| LOW | tools/metrics/sana_wm/eval_unified.py | 325 | def _vbench_torch_load_compat(): | CODE |
| LOW | tools/metrics/sana_wm/aggregate_results.py | 111 | def _compute_vbench_total_local(scores: dict[str, float]) -> dict[str, float]: | CODE |
| LOW | tools/metrics/sana_wm/aggregate_results.py | 133 | def _recompute_vbench_from_raw(eval_dir: str) -> dict[str, float]: | CODE |
| LOW | tools/metrics/sana_wm/eval_benchmark_poses.py | 50 | def _dataset_root_from_manifest(manifest_path: str) -> str: | CODE |
| LOW | tools/metrics/sana_wm/eval_benchmark_poses.py | 154 | def _resolve_skip_first_frame(arg_val: str, result_folder: str) -> bool: | CODE |
| LOW | tools/metrics/geneval/prompts/create_prompts.py | 38 | def generate_single_object_sample(rng: np.random.Generator, size: int = None): | CODE |
| LOW | tools/metrics/geneval/prompts/create_prompts.py | 62 | def generate_two_object_sample(rng: np.random.Generator): | CODE |
| LOW | tools/metrics/geneval/prompts/create_prompts.py | 128 | def generate_color_attribution_sample(rng: np.random.Generator): | CODE |
| LOW | tools/metrics/clip-score/clip_score.py | 231 | def calculate_clip_score_official(dataloader): | CODE |
| LOW | tools/metrics/pytorch-fid/compute_fid.py | 90 | def calculate_frechet_distance(mu1, sigma1, mu2, sigma2, eps=1e-6): | CODE |
| LOW | tools/metrics/pytorch-fid/compute_fid.py | 123 | def calculate_activation_statistics(files, model, batch_size=50, dims=2048, device="cpu", num_workers=1): | CODE |
| LOW | tools/metrics/pytorch-fid/compute_fid.py | 130 | def compute_statistics_of_path(path, model, batch_size, dims, device, num_workers=1, flag="ref"): | CODE |
| LOW | tools/metrics/pytorch-fid/compute_fid.py | 168 | def calculate_fid_given_paths(paths, batch_size, device, dims, num_workers=1): | CODE |
| LOW | tools/metrics/pytorch-fid/tests/test_fid_score.py | 13 | def test_calculate_fid_given_statistics(mocker, tmp_path, device): | CODE |
| LOW | tools/metrics/pytorch-fid/tests/test_fid_score.py | 41 | def test_compute_statistics_of_path(mocker, tmp_path, device): | CODE |
| LOW | tools/metrics/pytorch-fid/tests/test_fid_score.py | 62 | def test_compute_statistics_of_path_from_file(mocker, tmp_path, device): | CODE |
| LOW | tools/metrics/pytorch-fid/src/pytorch_fid/fid_score.py | 153 | def calculate_frechet_distance(mu1, sigma1, mu2, sigma2, eps=1e-6): | CODE |
| LOW | tools/metrics/pytorch-fid/src/pytorch_fid/fid_score.py | 206 | def calculate_activation_statistics(files, model, batch_size=50, dims=2048, device="cpu", num_workers=1): | CODE |
| LOW | tools/metrics/pytorch-fid/src/pytorch_fid/fid_score.py | 230 | def compute_statistics_of_path(path, model, batch_size, dims, device, num_workers=1): | CODE |
| LOW | tools/metrics/pytorch-fid/src/pytorch_fid/fid_score.py | 242 | def calculate_fid_given_paths(paths, batch_size, device, dims, num_workers=1): | CODE |
| LOW | train_video_scripts/train_sana_wm_stage1.py | 76 | def _resolve_cp_runtime_config(config: SanaVideoCamCtrlConfig) -> object: | CODE |
| LOW | train_video_scripts/train_sana_wm_stage1.py | 141 | def _build_parallelism_config(config: SanaVideoCamCtrlConfig, cp_size: int): | CODE |
| LOW | train_video_scripts/train_sana_wm_stage1.py | 179 | def _resolve_data_dirs_under_root(data_dir, root: str): | CODE |
| LOW | train_video_scripts/train_sana_wm_stage1.py | 219 | def _remove_custom_module_call(model, logger) -> None: | CODE |
| LOW | train_video_scripts/train_sana_wm_stage1.py | 271 | def _right_pad_temporal_with_last_frame(tensor: torch.Tensor, dim: int, pad_size: int) -> torch.Tensor: | CODE |
| LOW | train_video_scripts/train_sana_wm_stage1.py | 282 | def _map_global_chunk_index_to_local( | CODE |
| LOW | app/sana_pipeline.py | 52 | def classify_height_width_bin(height: int, width: int, ratios: dict) -> Tuple[int, int]: | CODE |
| LOW | app/sana_controlnet_pipeline.py | 54 | def classify_height_width_bin(height: int, width: int, ratios: dict) -> Tuple[int, int]: | CODE |
| LOW | app/sana_pipeline_inpaint.py | 56 | def classify_height_width_bin(height: int, width: int, ratios: dict) -> Tuple[int, int]: | CODE |
| LOW | app/sana_sprint_pipeline.py | 40 | def classify_height_width_bin(height: int, width: int, ratios: dict) -> Tuple[int, int]: | CODE |
| LOW | tests/test_sana_video2.py | 35 | def test_causal_encoder_reuses_the_diffusers_encoder_weights(): | CODE |
| LOW | tests/test_sana_video2.py | 66 | def test_released_model_dimensions_and_parameter_counts(): | CODE |
| LOW | tests/test_sana_video2.py | 79 | def test_attention_residual_buffer_matches_training_path(): | CODE |
| LOW | tests/test_sana_video2.py | 94 | def test_adaln_modulation_includes_the_learned_table(): | CODE |
| LOW | tests/test_sana_video2.py | 110 | def test_scalar_and_per_token_attnres_paths_match_in_eval(): | CODE |
| LOW | tests/test_sana_video2.py | 137 | def test_checkpoint_parameter_names_are_preserved(): | CODE |
| LOW | tests/test_sana_video2.py | 160 | def test_gated_linear_attention_removes_canceled_relu_normalizer(): | CODE |
| LOW | tests/test_sana_video2.py | 191 | def test_null_caption_embedding_can_be_loaded(tmp_path): | CODE |
| LOW | tests/test_sana_video2.py | 214 | def test_public_configs_select_released_models_and_video_only_training(): | CODE |
| LOW | tests/test_sana_video2.py | 234 | def test_release_demo_prompt_command_and_links_stay_in_sync(): | CODE |
| LOW | tests/test_fastvideo_dmd_sampler.py | 47 | def test_sampler_matches_manual_rng_reference(profile: str) -> None: | CODE |
| LOW | tests/test_fastvideo_dmd_sampler.py | 105 | def test_dmd_schedule_suffix_ignores_irrelevant_flow_shift() -> None: | CODE |
| LOW | tests/test_fastvideo_dmd_sampler.py | 124 | def test_ema_export_wrapper_discards_training_state() -> None: | CODE |
| LOW | tests/test_sana_cli_run.py | 26 | def test_hf_token_is_forwarded_without_cli_login(monkeypatch, conda_available): | CODE |
| LOW | tests/bash/training/test_training_sana_wm_distill.sh | 128 | def configure_self_forcing_data(cfg): | CODE |
| LOW | tests/bash/training/test_training_sana_streaming.sh | 136 | def test_bidirectional_pair_dataset(): | CODE |
| LOW | tests/bash/training/test_training_sana_streaming.sh | 185 | def test_read_video_from_path(): | CODE |
| LOW | tests/bash/training/test_training_sana_streaming.sh | 251 | def test_training_pipeline_cache_helpers(): | CODE |
| LOW | tests/bash/training/test_training_sana_streaming.sh | 417 | def test_training_pipeline_multi_chunk_conditioning(): | CODE |
| LOW | tests/bash/training/test_training_sana_streaming.sh | 463 | def test_reverse_reg_pipeline(): | CODE |
| LOW | tests/bash/training/test_training_sana_streaming.sh | 526 | def test_reverse_overlap_uses_only_new_frames(): | CODE |
| LOW⚡ | diffusion/post_training/rewards.py | 97 | def _get_clip_image_transform(processor): | CODE |
| LOW⚡ | diffusion/post_training/rewards.py | 114 | def _patch_imagereward_compat(): | CODE |
| LOW⚡ | diffusion/post_training/rewards.py | 124 | def _apply_chunking_to_forward(forward_fn, chunk_size, chunk_dim, *input_tensors): | CODE |
| LOW | diffusion/post_training/rewards.py | 136 | def _find_pruneable_heads_and_indices(heads, n_heads, head_size, already_pruned_heads): | CODE |
| 258 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | environment_setup.sh | 1 | #!/usr/bin/env bash | COMMENT |
| LOW | tools/create_wids_metadata.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | tools/download.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | tools/convert_sana_wm_refiner_to_diffusers.py | 1 | #!/usr/bin/env python3 | COMMENT |
| LOW | tools/controlnet/inference_controlnet.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | train_video_scripts/train_video_ivjoint_chunk.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | train_video_scripts/train_video_ivjoint.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | app/app_sana_multithread.py | 1 | #!/usr/bin/env python | COMMENT |
| LOW | app/sana_pipeline.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | app/sana_controlnet_pipeline.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | app/sana_pipeline_inpaint.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | app/safety_check.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | app/app_sana_4bit.py | 1 | #!/usr/bin/env python | COMMENT |
| LOW | app/app_sana.py | 1 | #!/usr/bin/env python | COMMENT |
| LOW | app/sana_sprint_pipeline.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | app/app_sana_sprint.py | 1 | #!/usr/bin/env python | COMMENT |
| LOW | asset/examples.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | asset/docs/quantize/8bit_sana.md | 1 | <!-- Copyright 2024 The HuggingFace Team. All rights reserved. | COMMENT |
| LOW | asset/docs/quantize/4bit_sana.md | 1 | <!--Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | tests/test_sana_video2.py | 1 | # Copyright 2026 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | tests/test_fastvideo_dmd_sampler.py | 1 | # Copyright 2026 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | tests/test_sana_cli_run.py | 1 | # Copyright 2026 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | sana/tools/hf_utils.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | sana/cli/run.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | sana/cli/upload2hf.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES (authored by @Lyken17) | COMMENT |
| LOW | diffusion/post_training/diffusers_patch/text_encode.py | 1 | #!/usr/bin/env python | COMMENT |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/guiders/adaptive_projected_guidance.py | 1 | # Copyright 2025 The HuggingFace Team. All rights reserved. | COMMENT |
| LOW | diffusion/scheduler/sana_streaming_cache.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/scheduler/dpm_solver.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/scheduler/scm_scheduler.py | 1 | # Copyright 2023 Stanford University Team and The HuggingFace Team. All rights reserved. | COMMENT |
| LOW | diffusion/scheduler/flow_euler_sampler.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/scheduler/iddpm.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/scheduler/sa_sampler.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/scheduler/lcm_scheduler.py | 1 | # Copyright 2023 Stanford University Team and The HuggingFace Team. All rights reserved. | COMMENT |
| LOW | diffusion/scheduler/fastvideo_dmd_sampler.py | 1 | # Copyright 2026 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/scheduler/sana_streaming_sampler.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/scheduler/trigflow_scheduler.py | 1 | # Copyright 2023 Stanford University Team and The HuggingFace Team. All rights reserved. | COMMENT |
| LOW | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 121 | # | COMMENT |
| LOW | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 501 | # over [sink + window + current], cached tokens already have the | COMMENT |
| LOW | diffusion/scheduler/sa_solver_diffusers.py | 1 | # Licensed under the Apache License, Version 2.0 (the "License"); | COMMENT |
| LOW | diffusion/utils/lr_scheduler.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/utils/camctrl_config.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/utils/misc.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/utils/config.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/utils/checkpoint.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/utils/chunk_utils.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/utils/logger.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/utils/action_overlay.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/utils/optimizer.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/utils/cam_utils.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/utils/dist_utils.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/model/model_growth_utils.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/model/respace.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/model/dpm_solver.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/model/registry.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/model/timestep_sampler.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/model/diffusion_utils.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| LOW | diffusion/model/edm_sample.py | 1 | # Copyright 2024 NVIDIA CORPORATION & AFFILIATES | COMMENT |
| 133 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | tools/create_wids_metadata.py | 32 | CODE | |
| LOW | tools/convert_sana_wm_refiner_to_diffusers.py | 135 | CODE | |
| LOW | tools/metrics/utils.py | 4 | CODE | |
| LOW | tools/metrics/sana_wm/eval_unified.py | 378 | CODE | |
| LOW | tools/metrics/sana_wm/eval_unified.py | 673 | CODE | |
| LOW | tools/metrics/sana_wm/eval_unified.py | 1053 | CODE | |
| LOW | tools/metrics/sana_wm/pose_utils.py | 128 | CODE | |
| LOW | tools/metrics/sana_wm/eval_benchmark_poses.py | 177 | CODE | |
| LOW | tools/metrics/geneval/evaluation/evaluate_images.py | 151 | CODE | |
| LOW | tools/metrics/geneval/generation/diffusers_generate.py | 84 | CODE | |
| LOW | tools/metrics/clip-score/clip_score.py | 85 | CODE | |
| LOW | tools/metrics/clip-score/clip_score.py | 106 | CODE | |
| LOW | tools/metrics/dpg_bench/compute_dpg_bench.py | 132 | CODE | |
| LOW | tools/metrics/pytorch-fid/compute_fid.py | 130 | CODE | |
| LOW | tools/convert_scripts/convert_sana_to_svdquant.py | 47 | CODE | |
| LOW | tools/convert_scripts/convert_sana_to_diffusers.py | 47 | CODE | |
| LOW | …ols/convert_scripts/convert_sana_video_to_diffusers.py | 33 | CODE | |
| LOW | …t_scripts/convert_ImgDataset_to_WebDatasetMS_format.py | 13 | CODE | |
| LOW | train_video_scripts/train_longsana.py | 30 | CODE | |
| LOW | train_video_scripts/train_sana_wm_stage1.py | 456 | CODE | |
| LOW | train_video_scripts/train_sana_wm_stage1.py | 520 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint_chunk.py | 109 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint_chunk.py | 282 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint_chunk.py | 875 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint_chunk.py | 123 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint.py | 240 | CODE | |
| LOW | train_video_scripts/train_video_ivjoint.py | 739 | CODE | |
| LOW | app/sana_pipeline.py | 167 | CODE | |
| LOW | app/sana_controlnet_pipeline.py | 190 | CODE | |
| LOW | app/sana_pipeline_inpaint.py | 324 | CODE | |
| LOW | app/app_sana_inpaint.py | 44 | CODE | |
| LOW | app/app_sana_inpaint.py | 278 | CODE | |
| LOW | sana/cli/upload2hf.py | 50 | CODE | |
| LOW | diffusion/post_training/ema.py | 27 | CODE | |
| LOW | diffusion/post_training/diffusers_patch/solver.py | 15 | CODE | |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 1461 | CODE | |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 1745 | CODE | |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 2005 | CODE | |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 2485 | CODE | |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 1044 | CODE | |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 2439 | CODE | |
| LOW | …usion/distributed/context_parallel/distributed_scan.py | 192 | CODE | |
| LOW | diffusion/guiders/adaptive_projected_guidance.py | 106 | CODE | |
| LOW | diffusion/scheduler/sana_streaming_cache.py | 22 | CODE | |
| LOW | diffusion/scheduler/lcm_scheduler.py | 175 | CODE | |
| LOW | diffusion/scheduler/longlive_flow_euler_sampler.py | 420 | CODE | |
| LOW | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 74 | CODE | |
| LOW | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 675 | CODE | |
| LOW | diffusion/scheduler/sa_solver_diffusers.py | 138 | CODE | |
| LOW | diffusion/scheduler/sa_solver_diffusers.py | 334 | CODE | |
| LOW | diffusion/scheduler/sa_solver_diffusers.py | 414 | CODE | |
| LOW | diffusion/scheduler/sa_solver_diffusers.py | 438 | CODE | |
| LOW | diffusion/scheduler/sa_solver_diffusers.py | 482 | CODE | |
| LOW | diffusion/utils/misc.py | 317 | CODE | |
| LOW | diffusion/utils/checkpoint.py | 138 | CODE | |
| LOW | diffusion/utils/logger.py | 197 | CODE | |
| LOW | diffusion/utils/optimizer.py | 52 | CODE | |
| LOW | diffusion/utils/optimizer.py | 325 | CODE | |
| LOW | diffusion/utils/optimizer.py | 501 | CODE | |
| LOW | diffusion/utils/optimizer.py | 623 | CODE | |
| 142 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | app/app_sana_controlnet_hed.py | 0 | <div style='display: flex; align-items: center; justify-content: center; text-align: center;'> <img src="https://nvlabs. | STRING |
| HIGH | app/app_sana_multithread.py | 0 | <div style='display: flex; align-items: center; justify-content: center; text-align: center;'> <img src="https://nvlabs. | STRING |
| HIGH | app/app_sana.py | 0 | <div style='display: flex; align-items: center; justify-content: center; text-align: center;'> <img src="https://nvlabs. | STRING |
| HIGH | app/app_sana_inpaint.py | 0 | <div style='display: flex; align-items: center; justify-content: center; text-align: center;'> <img src="https://nvlabs. | STRING |
| HIGH | scripts/interface.py | 0 | <div style='display: flex; align-items: center; justify-content: center; text-align: center;'> <img src="https://nvlabs. | STRING |
| HIGH | app/app_sana_4bit.py | 0 | <div style='display: flex; align-items: center; justify-content: center; text-align: center;'> <img src="https://nvlabs. | STRING |
| HIGH | app/app_sana_sprint.py | 0 | <div style='display: flex; align-items: center; justify-content: center; text-align: center;'> <img src="https://nvlabs. | STRING |
| HIGH | diffusion/scheduler/scm_scheduler.py | 0 | output class for the scheduler's `step` function output. args: prev_sample (`torch.floattensor` of shape `(batch_size, n | STRING |
| HIGH | diffusion/scheduler/lcm_scheduler.py | 0 | output class for the scheduler's `step` function output. args: prev_sample (`torch.floattensor` of shape `(batch_size, n | STRING |
| HIGH | diffusion/scheduler/trigflow_scheduler.py | 0 | output class for the scheduler's `step` function output. args: prev_sample (`torch.floattensor` of shape `(batch_size, n | STRING |
| HIGH | diffusion/scheduler/scm_scheduler.py | 0 | sets the discrete timesteps used for the diffusion chain (to be run before inference). args: num_inference_steps (`int`) | STRING |
| HIGH | diffusion/scheduler/lcm_scheduler.py | 0 | sets the discrete timesteps used for the diffusion chain (to be run before inference). args: num_inference_steps (`int`) | STRING |
| HIGH | diffusion/scheduler/trigflow_scheduler.py | 0 | sets the discrete timesteps used for the diffusion chain (to be run before inference). args: num_inference_steps (`int`) | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale_controlnet.py | 0 | forward pass of sanaums. x: (n, c, h, w) tensor of spatial inputs (images or latent representations of images) t: (n,) t | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale_adaln.py | 0 | forward pass of sanaums. x: (n, c, h, w) tensor of spatial inputs (images or latent representations of images) t: (n,) t | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale.py | 0 | forward pass of sanaums. x: (n, c, h, w) tensor of spatial inputs (images or latent representations of images) t: (n,) t | STRING |
| HIGH | diffusion/model/nets/sana.py | 0 | forward pass of sanaums. x: (n, c, h, w) tensor of spatial inputs (images or latent representations of images) t: (n,) t | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale_video.py | 0 | forward pass of sanaums. x: (n, c, h, w) tensor of spatial inputs (images or latent representations of images) t: (n,) t | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale_video_v2v.py | 0 | forward pass of sanaums. x: (n, c, h, w) tensor of spatial inputs (images or latent representations of images) t: (n,) t | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale_video_camctrl.py | 0 | forward pass of sanaums. x: (n, c, h, w) tensor of spatial inputs (images or latent representations of images) t: (n,) t | STRING |
| HIGH | diffusion/model/nets/sana_U_shape.py | 0 | forward pass of sanaums. x: (n, c, h, w) tensor of spatial inputs (images or latent representations of images) t: (n,) t | STRING |
| HIGH | diffusion/model/nets/sana_U_shape_multi_scale.py | 0 | forward pass of sanaums. x: (n, c, h, w) tensor of spatial inputs (images or latent representations of images) t: (n,) t | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale_controlnet.py | 0 | this method allows the object to be called like a function. it simply calls the forward method. | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale_video.py | 0 | this method allows the object to be called like a function. it simply calls the forward method. | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale.py | 0 | this method allows the object to be called like a function. it simply calls the forward method. | STRING |
| HIGH | diffusion/model/nets/sana.py | 0 | this method allows the object to be called like a function. it simply calls the forward method. | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale_video.py | 0 | a sana block with global shared adaptive layer norm zero (adaln-zero) conditioning. | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale_video_camctrl.py | 0 | a sana block with global shared adaptive layer norm zero (adaln-zero) conditioning. | STRING |
| HIGH | diffusion/model/nets/sana_multi_scale.py | 0 | a sana block with global shared adaptive layer norm zero (adaln-zero) conditioning. | STRING |
| HIGH | …inear/modules/triton_lite_mla_kernels/pad_vk_mm_fwd.py | 0 | kernel for computing the matmul c = a x b. a has shape (m, k), b has shape (k, n) and c has shape (m, n) | STRING |
| HIGH | …ear/modules/triton_lite_mla_kernels/linear_relu_fwd.py | 0 | kernel for computing the matmul c = a x b. a has shape (m, k), b has shape (k, n) and c has shape (m, n) | STRING |
| HIGH | …ear/modules/triton_lite_mla_kernels/proj_divide_bwd.py | 0 | kernel for computing the matmul c = a x b. a has shape (m, k), b has shape (k, n) and c has shape (m, n) | STRING |
| HIGH | …/nets/fastlinear/modules/triton_lite_mla_kernels/mm.py | 0 | kernel for computing the matmul c = a x b. a has shape (m, k), b has shape (k, n) and c has shape (m, n) | STRING |
| HIGH | scripts/inference_geneval.py | 0 | \ @article{ghosh2024geneval, title={geneval: an object-focused framework for evaluating text-to-image alignment}, author | STRING |
| HIGH | scripts/inference_geneval_diffusers.py | 0 | \ @article{ghosh2024geneval, title={geneval: an object-focused framework for evaluating text-to-image alignment}, author | STRING |
| HIGH | scripts/inference_sana_sprint_geneval.py | 0 | \ @article{ghosh2024geneval, title={geneval: an object-focused framework for evaluating text-to-image alignment}, author | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | tools/metrics/sana_wm/eval_unified.py | 296 | except Exception: | CODE |
| HIGH | tools/metrics/sana_wm/eval_unified.py | 306 | except Exception: | CODE |
| HIGH | tools/metrics/sana_wm/eval_unified.py | 1348 | except (json.JSONDecodeError, OSError): | CODE |
| HIGH | tools/metrics/sana_wm/eval_unified.py | 504 | except (json.JSONDecodeError, KeyError): | CODE |
| HIGH | train_video_scripts/train_video_ivjoint_chunk.py | 1512 | except: | CODE |
| HIGH | train_video_scripts/train_video_ivjoint.py | 1302 | except: | CODE |
| HIGH | train_video_scripts/train_video_ivjoint.py | 483 | except Exception: | CODE |
| HIGH | diffusion/refiner/diffusers_ltx2_refiner.py | 194 | except OSError: | CODE |
| HIGH | diffusion/scheduler/longlive_flow_euler_sampler.py | 307 | except Exception: | CODE |
| HIGH | diffusion/model/builder.py | 341 | except: | CODE |
| HIGH | diffusion/model/builder.py | 388 | except: | CODE |
| HIGH | …line/sana_inference_interactive_pipeline_long_chunk.py | 176 | except Exception: | CODE |
| HIGH | …line/sana_inference_interactive_pipeline_long_chunk.py | 198 | except Exception: | CODE |
| HIGH | …line/sana_inference_interactive_pipeline_long_chunk.py | 211 | except Exception: | CODE |
| HIGH | …line/sana_inference_interactive_pipeline_long_chunk.py | 250 | except Exception: | CODE |
| HIGH | …ngsana/pipeline/sana_inference_interactive_pipeline.py | 192 | except Exception: | CODE |
| HIGH | …ngsana/pipeline/sana_inference_interactive_pipeline.py | 251 | except Exception: | CODE |
| HIGH | …ngsana/pipeline/sana_inference_interactive_pipeline.py | 265 | except Exception: | CODE |
| HIGH | …ngsana/pipeline/sana_inference_interactive_pipeline.py | 308 | except Exception: | CODE |
| HIGH | …ion/longsana/pipeline/sana_switch_training_pipeline.py | 114 | except Exception: | CODE |
| HIGH | diffusion/longsana/utils/model_wrapper.py | 147 | except Exception: | CODE |
| HIGH | diffusion/longsana/model/ode_regression_sana.py | 60 | except Exception: | CODE |
| HIGH | diffusion/longsana/model/ode_regression_sana.py | 144 | except Exception: | CODE |
| HIGH | diffusion/longsana/model/ode_regression_sana.py | 190 | except Exception: | CODE |
| HIGH | diffusion/longsana/model/dmd_sana.py | 292 | except Exception: | CODE |
| HIGH | diffusion/data/wids/wids_mmtar.py | 161 | except FileNotFoundError: | CODE |
| HIGH | diffusion/data/wids/wids_mmtar.py | 164 | except BlockingIOError: | CODE |
| HIGH | diffusion/data/wids/wids_dl.py | 53 | except FileNotFoundError: | CODE |
| HIGH | inference_video_scripts/wm/streaming_mp4_writer.py | 215 | except BrokenPipeError: | CODE |
| HIGH | inference_video_scripts/wm/streaming_mp4_writer.py | 240 | except Exception: | CODE |
| HIGH | inference_video_scripts/wm/inference_sana_wm.py | 1342 | except StopIteration: | CODE |
| HIGH | inference_video_scripts/wm/inference_sana_wm.py | 1120 | except OSError: | CODE |
| HIGH | train_scripts/train.py | 1045 | except: | CODE |
| HIGH | train_scripts/train_scm_ladd.py | 1433 | except: | CODE |
| HIGH | train_scripts/sol_rl/train_utils.py | 502 | except Exception: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | app/app_sana_multithread.py | 235 | CODE | |
| LOW | app/app_sana_multithread.py | 284 | CODE | |
| LOW | app/sana_pipeline.py | 167 | CODE | |
| LOW | app/sana_controlnet_pipeline.py | 190 | CODE | |
| LOW | app/sana_pipeline_inpaint.py | 324 | CODE | |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 24 | CODE | |
| LOW | app/app_sana_4bit.py | 175 | CODE | |
| LOW | app/app_sana.py | 239 | CODE | |
| LOW | app/sana_sprint_pipeline.py | 150 | CODE | |
| LOW | app/app_sana_sprint.py | 217 | CODE | |
| LOW | …post_training/diffusers_patch/pipeline_with_logprob.py | 38 | CODE | |
| LOW | …post_training/diffusers_patch/pipeline_with_logprob.py | 203 | CODE | |
| LOW | …post_training/diffusers_patch/pipeline_with_logprob.py | 352 | CODE | |
| LOW | diffusion/distributed/context_parallel/halo_exchange.py | 127 | CODE | |
| LOW | diffusion/guiders/adaptive_projected_guidance.py | 49 | CODE | |
| LOW | diffusion/scheduler/dpm_solver.py | 23 | CODE | |
| LOW | diffusion/scheduler/iddpm.py | 26 | CODE | |
| LOW | diffusion/scheduler/sa_sampler.py | 49 | CODE | |
| LOW | diffusion/scheduler/lcm_scheduler.py | 175 | CODE | |
| LOW | diffusion/scheduler/trigflow_scheduler.py | 100 | CODE | |
| LOW | diffusion/scheduler/longlive_flow_euler_sampler.py | 93 | CODE | |
| LOW | diffusion/scheduler/sa_solver_diffusers.py | 138 | CODE | |
| LOW | diffusion/utils/checkpoint.py | 30 | CODE | |
| LOW | diffusion/utils/checkpoint.py | 76 | CODE | |
| LOW | diffusion/utils/checkpoint.py | 138 | CODE | |
| LOW | diffusion/utils/checkpoint.py | 230 | CODE | |
| LOW | diffusion/utils/checkpoint.py | 264 | CODE | |
| LOW | diffusion/utils/dist_utils.py | 293 | CODE | |
| LOW | diffusion/model/dpm_solver.py | 266 | CODE | |
| LOW | diffusion/model/dpm_solver.py | 1504 | CODE | |
| LOW | diffusion/model/dpm_solver.py | 1545 | CODE | |
| LOW | diffusion/model/dpm_solver.py | 1789 | CODE | |
| LOW | diffusion/model/edm_sample.py | 32 | CODE | |
| LOW | diffusion/model/edm_sample.py | 88 | CODE | |
| LOW | diffusion/model/gaussian_diffusion.py | 633 | CODE | |
| LOW | diffusion/model/gaussian_diffusion.py | 666 | CODE | |
| LOW | diffusion/model/sa_solver.py | 211 | CODE | |
| LOW | diffusion/model/sa_solver.py | 892 | CODE | |
| LOW | diffusion/model/sa_solver.py | 1092 | CODE | |
| LOW | diffusion/model/sa_solver.py | 1291 | CODE | |
| LOW | diffusion/model/wan2_2/vae.py | 688 | CODE | |
| LOW | diffusion/model/ltx2/causal_vae.py | 471 | CODE | |
| LOW | diffusion/model/ltx2/causal_vae.py | 831 | CODE | |
| LOW | diffusion/model/ltx2/causal_vae.py | 1022 | CODE | |
| LOW | diffusion/model/ltx2/causal_vae.py | 1151 | CODE | |
| LOW | diffusion/model/ltx2/causal_vae.py | 1303 | CODE | |
| LOW | diffusion/model/ltx2/causal_vae.py | 1499 | CODE | |
| LOW | diffusion/model/nets/sana_multi_scale_controlnet.py | 87 | CODE | |
| LOW | diffusion/model/nets/sana_multi_scale_video.py | 71 | CODE | |
| LOW | diffusion/model/nets/sana_multi_scale_video.py | 345 | CODE | |
| LOW | diffusion/model/nets/sana_blocks.py | 277 | CODE | |
| LOW | diffusion/model/nets/sana_blocks.py | 305 | CODE | |
| LOW | diffusion/model/nets/sana_blocks.py | 402 | CODE | |
| LOW | diffusion/model/nets/sana_blocks.py | 509 | CODE | |
| LOW | diffusion/model/nets/sana_blocks.py | 638 | CODE | |
| LOW | diffusion/model/nets/sana_blocks.py | 689 | CODE | |
| LOW | diffusion/model/nets/sana_blocks.py | 731 | CODE | |
| LOW | diffusion/model/nets/sana_blocks.py | 779 | CODE | |
| LOW | diffusion/model/nets/sana_blocks.py | 1208 | CODE | |
| LOW | diffusion/model/nets/sana_blocks.py | 1252 | CODE | |
| 83 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | tools/metrics/sana_wm/eval_unified.py | 865 | except Exception as e: | CODE |
| LOW | tools/metrics/sana_wm/eval_unified.py | 296 | except Exception: | CODE |
| LOW | tools/metrics/sana_wm/eval_unified.py | 306 | except Exception: | CODE |
| LOW | tools/metrics/sana_wm/eval_unified.py | 464 | except Exception: | CODE |
| LOW | tools/metrics/sana_wm/eval_unified.py | 516 | except Exception: | CODE |
| LOW | tools/metrics/sana_wm/eval_unified.py | 666 | except Exception as e: | CODE |
| LOW | tools/metrics/sana_wm/pose_utils.py | 140 | except Exception as exc: | CODE |
| MEDIUM | tools/metrics/sana_wm/pose_utils.py | 141 | print(f"Error loading {video_path}: {exc}") | CODE |
| LOW | tools/metrics/sana_wm/pose_utils.py | 165 | except Exception as exc: | CODE |
| LOW | tools/metrics/sana_wm/pose_utils.py | 180 | except Exception as exc: | CODE |
| MEDIUM | tools/metrics/sana_wm/pose_utils.py | 181 | print(f"Error inferencing {video_paths[valid_index]}: {exc}") | CODE |
| MEDIUM | tools/metrics/sana_wm/eval_benchmark_poses.py | 211 | print("Error: Pi3 not found. Install Pi3 or place it on PYTHONPATH.") | CODE |
| LOW | tools/metrics/sana_wm/eval_benchmark_poses.py | 334 | except Exception as e: | CODE |
| MEDIUM | tools/metrics/sana_wm/eval_benchmark_poses.py | 335 | print(f"Error evaluating {scene_id}: {e}") | CODE |
| LOW | tools/metrics/clip-score/clip_score.py | 199 | except Exception as e: | CODE |
| MEDIUM | tools/metrics/clip-score/clip_score.py | 179 | def process_sample(sample): | CODE |
| LOW | tools/metrics/dpg_bench/compute_dpg_bench.py | 246 | except Exception as e: | CODE |
| LOW | tools/metrics/pytorch-fid/compute_fid.py | 42 | except Exception as e: | CODE |
| LOW⚡ | …t_scripts/convert_ImgDataset_to_WebDatasetMS_format.py | 52 | except Exception as e: | CODE |
| MEDIUM⚡ | …t_scripts/convert_ImgDataset_to_WebDatasetMS_format.py | 53 | print(f"Error processing file {filename}: {e}") | CODE |
| LOW | train_video_scripts/train_video_ivjoint.py | 370 | except Exception as e: | CODE |
| MEDIUM | train_video_scripts/train_video_ivjoint.py | 371 | print(f"Error in vae_encode: {e}") | CODE |
| LOW | train_video_scripts/train_video_ivjoint.py | 483 | except Exception: | CODE |
| LOW | app/app_sana_inpaint.py | 253 | except Exception as e: | CODE |
| LOW | app/app_sana_inpaint.py | 264 | except Exception as e: | CODE |
| LOW | app/app_sana_inpaint.py | 469 | except Exception as e: | CODE |
| LOW | sana/tools/hf_utils.py | 97 | except Exception as e: | CODE |
| MEDIUM | sana/tools/hf_utils.py | 98 | print(f"Error downloading file: {e}") | CODE |
| LOW⚡ | diffusion/refiner/diffusers_ltx2_refiner.py | 2310 | except Exception: | CODE |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 91 | except Exception as exc: | CODE |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 161 | except Exception: | CODE |
| LOW | diffusion/refiner/diffusers_ltx2_refiner.py | 187 | except Exception as exc: | CODE |
| LOW | diffusion/scheduler/longlive_flow_euler_sampler.py | 307 | except Exception: | CODE |
| LOW | diffusion/scheduler/longlive_flow_euler_sampler.py | 351 | except Exception: | CODE |
| LOW | diffusion/utils/git.py | 167 | except Exception as e: | CODE |
| LOW | diffusion/utils/checkpoint.py | 170 | except Exception as exc: | CODE |
| LOW | diffusion/utils/action_overlay.py | 138 | except Exception: | CODE |
| LOW | diffusion/model/nets/sana_multi_scale_video.py | 1013 | except Exception as e: | CODE |
| MEDIUM | diffusion/model/nets/sana_multi_scale_video.py | 1014 | print(f"Error loading {key}: {e}") | CODE |
| LOW | diffusion/model/nets/sana_multi_scale_video_camctrl.py | 1527 | except Exception as e: | CODE |
| LOW | diffusion/model/nets/sana.py | 402 | except Exception as e: | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/image.py | 69 | except Exception: | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/image.py | 177 | except Exception: | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/dist.py | 43 | except Exception: | CODE |
| LOW | diffusion/model/ops/fused_gdn.py | 1719 | except Exception as e: | CODE |
| LOW | diffusion/model/ops/fused_gdn.py | 2086 | except Exception as e: | CODE |
| LOW | diffusion/model/ops/fused_gdn_chunkwise_cuda.py | 741 | except Exception: | CODE |
| LOW | diffusion/model/ops/fused_gdn_chunkwise_cuda.py | 827 | except Exception as e: # missing toolkit / unexpected shape -> Triton | CODE |
| LOW | diffusion/model/ops/fused_gdn_chunkwise_cuda.py | 906 | except Exception as e: # missing toolkit / unexpected shape -> Triton | CODE |
| LOW⚡ | diffusion/model/ops/fused_gdn_chunkwise.py | 1156 | except Exception: | CODE |
| LOW | …line/sana_inference_interactive_pipeline_long_chunk.py | 29 | except Exception: | CODE |
| LOW | …line/sana_inference_interactive_pipeline_long_chunk.py | 176 | except Exception: | CODE |
| LOW | …line/sana_inference_interactive_pipeline_long_chunk.py | 198 | except Exception: | CODE |
| LOW | …line/sana_inference_interactive_pipeline_long_chunk.py | 211 | except Exception: | CODE |
| LOW | …line/sana_inference_interactive_pipeline_long_chunk.py | 247 | except Exception as e: | CODE |
| LOW | …line/sana_inference_interactive_pipeline_long_chunk.py | 250 | except Exception: | CODE |
| LOW | …ngsana/pipeline/sana_inference_interactive_pipeline.py | 32 | except Exception: | CODE |
| LOW | …ngsana/pipeline/sana_inference_interactive_pipeline.py | 192 | except Exception: | CODE |
| LOW | …ngsana/pipeline/sana_inference_interactive_pipeline.py | 251 | except Exception: | CODE |
| LOW | …ngsana/pipeline/sana_inference_interactive_pipeline.py | 265 | except Exception: | CODE |
| 57 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | …t_scripts/convert_ImgDataset_to_WebDatasetMS_format.py | 57 | # Create a TAR file and include all files | COMMENT |
| MEDIUM | app/safety_check.py | 16 | # This file is copy from https://github.com/mit-han-lab/hart/blob/main/hart/utils/safety_check.py | COMMENT |
| MEDIUM | diffusion/post_training/stat_tracking.py | 93 | # Create a mask for the current group. | COMMENT |
| MEDIUM | diffusion/utils/cam_utils.py | 77 | # Create the base (N, 4, 4) tensor (identity matrix padded) | COMMENT |
| MEDIUM | diffusion/model/dpm_solver.py | 17 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/model/nets/sana_multi_scale_controlnet.py | 19 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/model/nets/sana_multi_scale_video.py | 18 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/model/nets/sana_blocks.py | 17 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/model/nets/sana_multi_scale_adaln.py | 17 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/model/nets/sana_gdn_blocks.py | 70 | """This function is intended to align with the l2norm implementation in the FLA library.""" | STRING |
| MEDIUM | diffusion/model/nets/sana_U_shape.py | 17 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/model/nets/sana_multi_scale_video_camctrl.py | 18 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/model/nets/basic_modules.py | 17 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/model/nets/sana_U_shape_multi_scale.py | 17 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/model/nets/sana_multi_scale.py | 17 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/model/nets/sana.py | 17 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/data/datasets/sana_data_multi_scale.py | 18 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/data/datasets/sana_data.py | 17 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/data/datasets/utils.py | 17 | # This file is modified from https://github.com/PixArt-alpha/PixArt-sigma | COMMENT |
| MEDIUM | diffusion/data/wids/wids_tar.py | 17 | # This file is copied from https://github.com/NVlabs/VILA/tree/main/llava/wids | COMMENT |
| MEDIUM | diffusion/data/wids/wids_tar.py | 49 | # Create the index | COMMENT |
| MEDIUM | diffusion/data/wids/wids_tar.py | 59 | # Create an empty list for the index | COMMENT |
| MEDIUM | diffusion/data/wids/wids_mmtar.py | 17 | # This file is copied from https://github.com/NVlabs/VILA/tree/main/llava/wids | COMMENT |
| MEDIUM | diffusion/data/wids/__init__.py | 2 | # This file is part of the WebDataset library. | COMMENT |
| MEDIUM | diffusion/data/wids/wids_specs.py | 17 | # This file is copied from https://github.com/NVlabs/VILA/tree/main/llava/wids | COMMENT |
| MEDIUM | diffusion/data/wids/wids.py | 17 | # This file is modified from https://github.com/NVlabs/VILA/tree/main/llava/wids | COMMENT |
| MEDIUM | diffusion/data/wids/wids_dl.py | 17 | # This file is copied from https://github.com/NVlabs/VILA/tree/main/llava/wids | COMMENT |
| MEDIUM | diffusion/data/wids/wids_lru.py | 17 | # This file is copied from https://github.com/NVlabs/VILA/tree/main/llava/wids | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | app/safety_check.py | 23 | __all__ = ["is_dangerous"] | CODE |
| LOW⚡ | diffusion/refiner/diffusers_ltx2_refiner.py | 2345 | def set_value(owner: object, key: object, old_value: object, new_value: object, kind: str) -> None: | CODE |
| LOW | diffusion/distributed/context_parallel/config.py | 66 | def set_cp_runtime_config(config: CpRuntimeConfig) -> None: | CODE |
| LOW | diffusion/distributed/context_parallel/config.py | 77 | def set_cp_group(group: ProcessGroup | None) -> None: | CODE |
| LOW | diffusion/distributed/context_parallel/__init__.py | 29 | __all__ = [ | CODE |
| LOW | diffusion/guiders/__init__.py | 3 | __all__ = ["AdaptiveProjectedGuidance"] | CODE |
| LOW | diffusion/utils/import_utils.py | 8 | logger = logging.getLogger(__name__) | CODE |
| LOW | diffusion/model/act.py | 21 | __all__ = ["build_act", "get_act_name"] | CODE |
| LOW | diffusion/model/liger_norms.py | 33 | logger = logging.getLogger(__name__) | CODE |
| LOW | diffusion/model/norms.py | 23 | __all__ = ["LayerNorm2d", "build_norm", "get_norm_name", "reset_bn", "remove_bn", "set_norm_eps"] | CODE |
| LOW | diffusion/model/norms.py | 173 | def set_norm_eps(model: nn.Module, eps: float or None = None, momentum: float or None = None) -> None: | CODE |
| LOW | diffusion/model/wan2_2/vae.py | 13 | __all__ = [ | CODE |
| LOW | diffusion/model/ltx2/causal_vae.py | 203 | def update_tail(self, z: torch.Tensor, prepend_prev_latent_frames: int) -> None: | CODE |
| LOW | diffusion/model/nets/sana_blocks.py | 79 | def set_use_xformers(self, enabled: bool) -> None: | CODE |
| LOW | diffusion/model/nets/sana_video2.py | 299 | def set_cross_attention_xformers(self, enabled: bool) -> None: | CODE |
| LOW | diffusion/model/nets/sana_video2.py | 590 | __all__ = [ | CODE |
| LOW | diffusion/model/nets/fastlinear/modules/nn/norm.py | 24 | __all__ = ["LayerNorm2d", "build_norm", "get_norm_name", "reset_bn", "remove_bn", "set_norm_eps"] | CODE |
| LOW | diffusion/model/nets/fastlinear/modules/nn/norm.py | 174 | def set_norm_eps(model: nn.Module, eps: float or None = None, momentum: float or None = None) -> None: | CODE |
| LOW | diffusion/model/nets/fastlinear/modules/nn/act.py | 21 | __all__ = ["build_act", "get_act_name"] | CODE |
| LOW | diffusion/model/wan/attention.py | 25 | __all__ = [ | CODE |
| LOW | diffusion/model/wan/t5.py | 12 | __all__ = [ | CODE |
| LOW | diffusion/model/wan/__init__.py | 8 | __all__ = [ | CODE |
| LOW | diffusion/model/wan/model.py | 17 | __all__ = ["WanModel"] | CODE |
| LOW | diffusion/model/wan/clip.py | 17 | __all__ = [ | CODE |
| LOW | diffusion/model/wan/xlm_roberta.py | 7 | __all__ = ["XLMRoberta", "xlm_roberta_large"] | CODE |
| LOW | diffusion/model/wan/vae.py | 15 | __all__ = [ | CODE |
| LOW | diffusion/model/wan/tokenizers.py | 9 | __all__ = ["HuggingfaceTokenizer"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/ae_model_zoo.py | 38 | __all__ = ["create_dc_ae_model_cfg", "DCAE_HF", "AutoencoderKL"] | CODE |
| LOW | …/model/dc_ae/efficientvit/models/nn/triton_rms_norm.py | 21 | __all__ = ["TritonRMSNorm2dFunc"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/models/nn/norm.py | 26 | __all__ = ["LayerNorm2d", "TritonRMSNorm2d", "build_norm", "reset_bn", "set_norm_eps"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/models/nn/norm.py | 201 | def set_norm_eps(model: nn.Module, eps: Optional[float] = None) -> None: | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/models/nn/ops.py | 38 | __all__ = [ | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/models/nn/act.py | 24 | __all__ = ["build_act"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/models/nn/drop.py | 27 | __all__ = ["apply_drop_func"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/models/utils/list.py | 19 | __all__ = [ | CODE |
| LOW | …fusion/model/dc_ae/efficientvit/models/utils/random.py | 22 | __all__ = [ | CODE |
| LOW | …usion/model/dc_ae/efficientvit/models/utils/network.py | 26 | __all__ = [ | CODE |
| LOW | …/model/dc_ae/efficientvit/models/efficientvit/dc_ae.py | 41 | __all__ = ["DCAE", "dc_vae_f32", "dc_ae_f32c32", "dc_ae_f64c128", "dc_ae_f128c512"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/setup.py | 24 | __all__ = [ | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/misc.py | 22 | __all__ = [ | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/lr.py | 24 | __all__ = ["CosineLRwithWarmup", "ConstantLRwithWarmup"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/ema.py | 25 | __all__ = ["EMA"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/ema.py | 28 | def update_ema(ema: nn.Module, new_state_dict: dict[str, torch.Tensor], decay: float) -> None: | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/export.py | 26 | __all__ = ["export_onnx"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/opt.py | 21 | __all__ = ["REGISTERED_OPTIMIZER_DICT", "build_optimizer"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/metric.py | 23 | __all__ = ["AverageMeter"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/init.py | 23 | __all__ = ["init_modules", "zero_last_gamma"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/image.py | 26 | __all__ = ["load_image", "load_image_from_dir", "DMCrop", "CustomImageFolder", "ImageDataset"] | CODE |
| LOW | diffusion/model/dc_ae/efficientvit/apps/utils/dist.py | 25 | __all__ = [ | CODE |
| LOW | …on/model/dc_ae/efficientvit/apps/trainer/run_config.py | 25 | __all__ = ["Scheduler", "RunConfig"] | CODE |
| LOW | …on/model/dc_ae/efficientvit/apps/trainer/run_config.py | 107 | def update_global_step(self, epoch, batch_id=0) -> None: | CODE |
| LOW | diffusion/model/ops/fused_cam_gdn.py | 2432 | __all__ = [ | CODE |
| LOW | diffusion/model/ops/fused_gdn_chunkwise_stateful_bwd.py | 146 | __all__ = [ | CODE |
| LOW | diffusion/model/ops/fused_gdn_cp.py | 80 | __all__ = [ | CODE |
| LOW | diffusion/model/ops/__init__.py | 82 | __all__ = [ | CODE |
| LOW | diffusion/model/ops/fused_gdn_chunkwise_stateful_raw.py | 591 | __all__ = [ | CODE |
| LOW | diffusion/model/ops/frame_gdn/__init__.py | 5 | __all__ = ["_build_transition_matrices"] | CODE |
| LOW | diffusion/model/ops/frame_gdn/api.py | 51 | __all__ = ["_build_transition_matrices"] | CODE |
| LOW | diffusion/longsana/pipeline/__init__.py | 5 | __all__ = [ | CODE |
| LOW | diffusion/longsana/model/__init__.py | 5 | __all__ = ["DMDSana", "ODERegressionSana", "StreamingSANATrainingModel"] | CODE |
| 4 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 53 | # Step 1: Generate latent using Sana Video Pipeline | COMMENT |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 93 | # Step 2: Load LTX2 Pipeline | COMMENT |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 168 | # Step 3: Manually pack video latent (skip diffusers' normalize, consistent with original code) | COMMENT |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 180 | # Step 4: Create audio latent (becomes zero after normalize, consistent with original code) | COMMENT |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 202 | # Step 5: LTX2 Stage-2 Refinement | COMMENT |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 233 | # Step 6: Save output | COMMENT |
| LOW⚡ | diffusion/longsana/model/ode_regression_sana.py | 105 | # Step 1: Initialize all models | COMMENT |
| LOW | diffusion/longsana/model/ode_regression_sana.py | 126 | # Step 2: Initialize all hyperparameters | COMMENT |
| LOW | diffusion/longsana/model/ode_regression_sana.py | 327 | # Step 1: Run generator on noisy latents | COMMENT |
| LOW | diffusion/longsana/model/ode_regression_sana.py | 342 | # Step 2: Compute the regression loss | COMMENT |
| LOW | diffusion/longsana/model/dmd_sana.py | 689 | # Step 1: Sample noise and backward simulate the generator's input | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/self_forcing_trainer.py | 76 | # Step 2: Initialize the model | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/self_forcing_trainer.py | 79 | # Step 2: Initialize the model and optimizer | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 38 | # Step 1: Initialize the distributed training environment (rank, seed, dtype, logging etc.) | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 151 | # Step 4: Initialize the optimizer | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 165 | # Step 5: Initialize the dataloader | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 185 | # Step 6: Initialize the validation dataloader for visualization (fixed prompts) | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 466 | # Step 1: Get the next batch of text prompts | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 482 | # Step 2: Extract the conditional infos for sana | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 509 | # Step 3: Store gradients for the generator (if training the generator) | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 530 | # Step 4: Store gradients for the critic (if training the critic) | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/ode.py | 92 | # Step 4: Initialize the optimizer | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/ode.py | 100 | # Step 5: Initialize the dataloader | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/ode.py | 466 | # Step 1: Get the next batch of text prompts | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/ode.py | 471 | # Step 2: Extract the conditional infos | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/ode.py | 475 | # Step 3: Train the generator | COMMENT |
| LOW | diffusion/longsana/trainer/ode.py | 32 | # Step 1: Initialize the distributed training environment (rank, seed, dtype, logging etc.) | COMMENT |
| LOW | diffusion/longsana/trainer/ode.py | 69 | # Step 2: Initialize the model and optimizer | COMMENT |
| LOW | diffusion/longsana/trainer/ode.py | 111 | # Step 6: Initialize the validation dataloader for visualization (fixed prompts) | COMMENT |
| LOW | diffusion/longsana/trainer/ode.py | 512 | # Step 4: Visualization | COMMENT |
| LOW | diffusion/longsana/trainer/ode.py | 565 | # Step 5: Logging | COMMENT |
| LOW | inference_video_scripts/wm/inference_sana_wm.py | 116 | # NOTE: The default HF checkpoint is bidirectional and is incompatible with | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 53 | # Step 1: Generate latent using Sana Video Pipeline | COMMENT |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 93 | # Step 2: Load LTX2 Pipeline | COMMENT |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 168 | # Step 3: Manually pack video latent (skip diffusers' normalize, consistent with original code) | COMMENT |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 180 | # Step 4: Create audio latent (becomes zero after normalize, consistent with original code) | COMMENT |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 202 | # Step 5: LTX2 Stage-2 Refinement | COMMENT |
| LOW | app/sana_video_refiner_pipeline_diffusers.py | 233 | # Step 6: Save output | COMMENT |
| LOW⚡ | diffusion/longsana/model/ode_regression_sana.py | 105 | # Step 1: Initialize all models | COMMENT |
| LOW | diffusion/longsana/model/ode_regression_sana.py | 126 | # Step 2: Initialize all hyperparameters | COMMENT |
| LOW | diffusion/longsana/model/ode_regression_sana.py | 327 | # Step 1: Run generator on noisy latents | COMMENT |
| LOW | diffusion/longsana/model/ode_regression_sana.py | 342 | # Step 2: Compute the regression loss | COMMENT |
| LOW | diffusion/longsana/model/dmd_sana.py | 689 | # Step 1: Sample noise and backward simulate the generator's input | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/self_forcing_trainer.py | 76 | # Step 2: Initialize the model | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/self_forcing_trainer.py | 79 | # Step 2: Initialize the model and optimizer | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 38 | # Step 1: Initialize the distributed training environment (rank, seed, dtype, logging etc.) | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 151 | # Step 4: Initialize the optimizer | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 165 | # Step 5: Initialize the dataloader | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 185 | # Step 6: Initialize the validation dataloader for visualization (fixed prompts) | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 466 | # Step 1: Get the next batch of text prompts | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 482 | # Step 2: Extract the conditional infos for sana | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 509 | # Step 3: Store gradients for the generator (if training the generator) | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 530 | # Step 4: Store gradients for the critic (if training the critic) | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/ode.py | 92 | # Step 4: Initialize the optimizer | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/ode.py | 100 | # Step 5: Initialize the dataloader | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/ode.py | 466 | # Step 1: Get the next batch of text prompts | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/ode.py | 471 | # Step 2: Extract the conditional infos | COMMENT |
| LOW⚡ | diffusion/longsana/trainer/ode.py | 475 | # Step 3: Train the generator | COMMENT |
| LOW | diffusion/longsana/trainer/ode.py | 32 | # Step 1: Initialize the distributed training environment (rank, seed, dtype, logging etc.) | COMMENT |
| LOW | diffusion/longsana/trainer/ode.py | 69 | # Step 2: Initialize the model and optimizer | COMMENT |
| LOW | diffusion/longsana/trainer/ode.py | 111 | # Step 6: Initialize the validation dataloader for visualization (fixed prompts) | COMMENT |
| LOW | diffusion/longsana/trainer/ode.py | 512 | # Step 4: Visualization | COMMENT |
| LOW | diffusion/longsana/trainer/ode.py | 565 | # Step 5: Logging | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | diffusion/utils/chunk_utils.py | 76 | Convert chunk_size to chunk_index list with a split strategy. Args: T: Number of latent frames. chu | STRING |
| HIGH | diffusion/utils/chunk_utils.py | 135 | Resolve chunk_index from a config, supporting chunk_size and strategy. Priority: 1) config.model.chunk_index | STRING |
| HIGH | diffusion/utils/chunk_utils.py | 214 | Return frame-time positions belonging to size-1 (singleton) chunks. A size-1 chunk has no intra-chunk lookahead, so | STRING |
| HIGH | diffusion/utils/chunk_utils.py | 384 | Normalize chunk_index and detect if uniform. This function handles all the complex logic for: 1. Converting chu | STRING |
| HIGH | diffusion/model/model_growth_utils.py | 70 | Args: strategy: init strategy name **kwargs: strategy specific parameters Ret | STRING |
| HIGH | diffusion/model/ops/fused_cam_gdn.py | 1391 | Fused numerator-only single-path delta-rule scan for the cam branch. Args: q, k, v: ``(B, H, D, N)`` fp32 c | STRING |
| HIGH | diffusion/model/ops/fused_gdn_cp.py | 1022 | End-to-end differentiable CP fused GDN raw entry (num, den). Composes :class:`_CpFusedGdnPrep` -> :func:`cp_frame_g | STRING |
| HIGH | diffusion/model/ops/fused_gdn.py | 645 | One direction of fused BiGDN via the unified kernel. Args: qkv .. eps: see kernel signature. reverse: f | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | environment_setup.sh | 16 | # Check if we should skip environment setup entirely (used by CI). | COMMENT |
| LOW | tools/metrics/sana_wm/eval_unified.py | 901 | # Check if results already exist | COMMENT |
| LOW | app/app_sana_inpaint.py | 449 | # Check if this is a new image by comparing with stored original | COMMENT |
| LOW | diffusion/utils/chunk_utils.py | 342 | # Check if tail (sizes[1:]) is uniform | COMMENT |
| LOW | diffusion/utils/chunk_utils.py | 359 | # Check if tail (sizes[1:]) is uniform | COMMENT |
| LOW | diffusion/utils/chunk_utils.py | 418 | # Check if uniform (requires chunk_size for comparison) | COMMENT |
| LOW | diffusion/utils/chunk_utils.py | 446 | # Check if uniform | COMMENT |
| LOW | diffusion/utils/data_sampler.py | 262 | # Assign samples to each bucket | COMMENT |
| LOW | diffusion/model/utils.py | 136 | # Check if resizing is needed | COMMENT |
| LOW | diffusion/longsana/utils/dataset.py | 384 | # Check if all samples list length is consistent | COMMENT |
| LOW | diffusion/longsana/model/streaming_sana_long.py | 536 | # Check if previous_frames can be used for overlap and auto-compute overlap frame count | COMMENT |
| LOW | diffusion/longsana/trainer/self_forcing_trainer.py | 633 | # Check if we've reached max iterations | COMMENT |
| LOW | diffusion/longsana/trainer/longsana_trainer.py | 390 | # Check if we should train generator on this optimization step | COMMENT |
| LOW | diffusion/data/wids/wids.py | 644 | # Check if we're missing the cache too often. | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | tools/metrics/clip-score/clip_score.py | 50 | self.fake_data = self._load_txt_from_path(fake_path) | CODE |
| LOW | tools/metrics/clip-score/clip_score.py | 63 | fake_data = self._load_txt(self.fake_data[index]) | CODE |
| LOW | tools/metrics/clip-score/clip_score.py | 64 | sample = dict(real=real_data, fake=fake_data, prompt=self.fake_data[index]) | CODE |
| LOW | tools/metrics/clip-score/src/clip_score/clip_score.py | 93 | fake_data = self._load_modality(fake_path, self.fake_flag) | CODE |
| LOW | tools/metrics/clip-score/src/clip_score/clip_score.py | 95 | sample = dict(real=real_data, fake=fake_data) | CODE |
| LOW | tools/metrics/clip-score/src/clip_score/clip_score.py | 124 | fake_name = self.fake_folder[idx].split(".") | CODE |
| LOW | tools/metrics/clip-score/src/clip_score/clip_score.py | 125 | if fake_name != real_name: | CODE |
| LOW | diffusion/longsana/model/streaming_sana_long.py | 858 | if self.base_model.fake_name == "SANA": | CODE |
| LOW⚡ | diffusion/longsana/model/dmd_sana.py | 328 | fake_name = getattr(args, "fake_name", "SANA") | CODE |
| LOW⚡ | diffusion/longsana/model/dmd_sana.py | 329 | self.fake_name = fake_name | CODE |
| LOW⚡ | diffusion/longsana/model/dmd_sana.py | 330 | if fake_name == "SANA": | CODE |
| LOW | diffusion/longsana/model/dmd_sana.py | 394 | if self.fake_name == "SANA": | CODE |
| LOW | diffusion/longsana/model/dmd_sana.py | 516 | if self.fake_name == "SANA": | CODE |
| LOW | diffusion/longsana/model/dmd_sana.py | 876 | if self.fake_name == "SANA": | CODE |
| LOW | …a_streaming/train/sana_streaming_long_969_2b_720p.yaml | 12 | fake_name: SANA | CODE |
| LOW | …a_streaming/train/sana_streaming_long_441_2b_720p.yaml | 12 | fake_name: SANA | CODE |
| LOW | …igs/sana_video_config/longsana/480ms/self_forcing.yaml | 12 | fake_name: SANA | CODE |
| LOW | configs/sana_video_config/longsana/480ms/longsana.yaml | 14 | fake_name: SANA | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | asset/docs/sana_lora_dreambooth.md | 111 | - `report_to="wandb` will ensure the training runs are tracked on [Weights and Biases](https://wandb.ai/site). To use it | CODE |
| HIGH | docs/sana_lora_dreambooth.md | 111 | - `report_to="wandb` will ensure the training runs are tracked on [Weights and Biases](https://wandb.ai/site). To use it | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | environment_setup.sh | 8 | # Usage: | COMMENT |
| LOW | app/app_sana_inpaint.py | 315 | ### How to use: | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | diffusion/scheduler/self_forcing_flow_euler_sampler.py | 510 | # scaffolding. | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | diffusion/longsana/model/dmd_sana.py | 281 | # TODO: Need to make the path more robust. | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …t_scripts/convert_ImgDataset_to_WebDatasetMS_format.py | 13 | def process_data(input_dir, output_tar_name="output.tar"): | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | train_scripts/train_dreambooth_lora_sana.py | 1016 | # make sure to pop weight so that corresponding model is not saved again | STRING |