Skip to content

ATTRIBUTIONS.md

Latest commit

 

History

History
135 lines (111 loc) · 11.3 KB

ATTRIBUTIONS.md

File metadata and controls

135 lines (111 loc) · 11.3 KB
Raw

Attributions

diffusers-workflow is Apache-2.0. This page credits the work it builds on that a dependency list does not show: code that was copied in, and other projects whose ideas were reimplemented here. Python dependencies are in pyproject.toml. Model and LoRA weights keep their own licences, and each catalog entry (workflows/models/, loras/) names the repository it downloads from.

Code included in this repository

Each copied or ported file keeps its upstream licence notice in its header.

File Source Licence
dw/tasks/rife_model.py The RIFE interpolation network from hzwer/Practical-RIFE MIT, Copyright (c) Megvii Inc.
dw/tasks/h3_latent_upscaler_model.py The MiniMax H3 3D-convolution latent upscaler from LBH-123-AI/Comfyui_Minimax_h3_latent_Upscaler MIT, Copyright (c) LBH-123-AI
dw/vendored/audio8_tts_model.py The Audio8-TTS (ArkTTS) dual-AR speech model, codec and processor from Edge0/Audio8-TTS-Realistic-0.6b, ported (upstream NOTICE kept in the file header) Apache-2.0
dw/vendored/mmaudio_model.py, dw/vendored/mmaudio_clip.py The MMAudio flow-matching network, its sequence lengths and classifier-free guidance, and the CLIP conditioning from hkchengrex/MMAudio, ported (the sampler is dw's own Euler loop, and the DFN5B towers are transformers' CLIP models filled by a key map) MIT, Copyright (c) 2024 Sony Research Inc.
dw/vendored/mmaudio_sync_model.py MMAudio's Synchformer visual encoder (a MotionFormer feature extractor) and its 16-frame segmenting, from hkchengrex/MMAudio's mmaudio/ext/synchformer/, ported without timm, einops or omegaconf MIT, Copyright (c) 2024 Vladimir Iashin
dw/tasks/mmaudio_decoder.py Loads diffusers' MMAudioVAE and MMAudioVocoder; the vocoder is BigVGAN (no BigVGAN code is copied here: the classes are diffusers') BigVGAN: MIT, Copyright (c) 2024 NVIDIA CORPORATION
dw/community_pipelines/pipeline_flux_rf_inversion.py The diffusers community RF-Inversion pipeline, after RF Inversion by Litu Rout, Yujia Chen, Nataniel Ruiz, Constantine Caramanis, Sanjay Shakkottai and Wen-Sheng Chu Apache-2.0, Copyright 2024 Black Forest Labs and The HuggingFace Team
dw/prompt_weighting.py Based on sd_embed by Andrew Zhu Apache-2.0

Model weights with their own terms

Most weights are named only by their catalog entry. These are listed here as well, because their terms are narrower than this repository's licence and apply to anything generated with them.

Weights Used by Licence
hkchengrex/MMAudio (weights/mmaudio_large_44k_v2.pth and its ext_weights/) generate_sound_effects: dw/vendored/mmaudio_model.py CC-BY-NC 4.0: non-commercial use only
hkchengrex/MMAudio ext_weights/synchformer_state_dict.pth generate_sound_effects, MMAudio's sync features, dw/vendored/mmaudio_sync_model.py CC-BY-NC 4.0: non-commercial use only
kandinskylab/Kandinsky-6.0-Lite-distill-5s-Diffusers audio_vae/ and vocoder/ generate_sound_effects, MMAudio's decoder, dw/tasks/mmaudio_decoder.py The MMAudio VAE tensors: CC-BY-NC 4.0, non-commercial use only, as MMAudio's weights (K6's model card states MIT; dw follows the stricter MMAudio terms). The BigVGAN vocoder: MIT.
apple/DFN5B-CLIP-ViT-H-14-384 generate_sound_effects, MMAudio's CLIP conditioning, dw/vendored/mmaudio_clip.py Apple Machine Learning Research Model License: research purposes only. Apple Machine Learning Research Model is licensed under the Apple Machine Learning Research Model License Agreement. dw maps the weights into transformers' layout in memory at load time and never writes or ships converted tensors.

Ideas reimplemented here

These projects showed an approach that dw rebuilt in its own code for diffusers. No code, prompt text or data was copied from them; where a licence does not allow reuse, only the concept was taken. The issue numbers link to the design discussion, which names the source files consulted.

vrgamegirl19/comfyui-vrgamedevgirl

A ComfyUI node pack and set of workflows for MiniMax H3 and LTX-2 film making, assessed in October 2026. It is source-available under a licence that does not allow reuse here, so only concepts were taken. It inspired:

  • holding the reference audio during H3 denoising, and a refine pass after the latent upscale (#598)
  • tracked, distance-gated face repair with LTX on face crops (#599)
  • the music-video timing stack: beat analysis, a lyric- and beat-aware cut planner, pad-then-trim shots (#600)
  • overlapping windows for long video sources, joined with a cosine blend (window_video, join_windows; #601)
  • the exact size and frame-count round trip for video-to-video templates (fit_to_model, restore_to_source; #602)
  • the finishing tasks: LUT apply and make, film grain, sharpen, tonal controls in grade (#603)
  • stem separation as its own task (separate_stems; #604)
  • strength-selectable same-size LTX refine and per-segment strength decay in chains (#606)
  • laying out a reference sheet from individual images (ingredients_grid; #607)
  • the H3 dialogue-budget warnings (#608)
  • checking a take's transcript against the expected lines (check_script; #609)
  • the script-to-video shot-list contract and voice bible (#610)
  • H3 chunk continuation in latent space (#611)
  • trying the Alissonerdx H3 LoRAs, which its workflows use (#612)

Kablex/ComfyUI-Ref2VA-VSA

Apache-2.0. Showed that MiniMax H3's Ref2VA attention could run block-sparse, building on the FastVideo team's VSA-H3 sparse-attention work. dw's sparse attention backend (dw/sparse_attention.py, #931) runs on comfy-kitchen's Sol-Attn kernel, a dependency.

mo-akkakk/ComfyUI-MiniMaxH3-TemporalWindow-SpatialTiles

MIT. The tiled low-sigma refine after an H3 upscale (refine_tiles, #1043), and the approach of the test that checks a one-segment H3 chain is bit-identical to a native run on a tiny random-weight model on CPU (#1046).

harlixay7/Kinoloom

MIT. Its seamless-chain research gave analyze_seams its saturation, lightness, contrast and detail measures (#1031), and the script-to-video skill its guidance on re-rolling a chained segment whose seam fails (#1034).

r34vtraining/Longshot_Studio

A ComfyUI studio for making long MiniMax H3 films shot by shot, assessed in October 2026. It has no licence, so only concepts are taken. Its ideas are filed as dialogue/effects stem separation (#1091), an H3 face refine with the audio held (#1092), cutaway and lead-in joins (#1093), rendering the odd shots of a long take first and bridging the gaps (#1094), and finding phrase starts from the centre of the stereo mix (#1095).

knoic/ComfyUI-MiniMaxH3-PrefixStream

A ComfyUI node pack for MiniMax H3 prefix streaming, under the MIT licence. It inspired the texture-band measurement on compare_outputs (texture_bands, dw/texture_bands.py): RMS energy by wavelength band, to see whether a change in a chain adds or removes texture. It also inspired guide_noise (dw/pipeline_processors/h3_guide_steps.py; #1166), from its prefix noise at 775be90: a cosine-tapered noise on each guide, folded in as the difference of a paired VAE encode, so the guide's hold loosens toward its start.

1113800942/comfy-h3md-director

H3MD Director, a ComfyUI node pack for directing long MiniMax H3 videos, under AGPL-3.0-or-later, so only the concept was taken. It inspired the latent statistics anchor: rescaling each later segment's video latent to the first segment's per-channel mean and standard deviation before decode (latent_anchor, chain.anchor: "segment_1", dw/pipeline_processors/h3_anchor.py; #1166). The diagnosis it answers, colour and contrast drifting from segment to segment of an H3 chain, was described by Lumifel and by roycho87 (NerdNotes).