Raynold van Heyningen 99073836d4 Fix MiniMax Music 3 producing noise with CUDA graphs enabled. (#16428) ...

The AR decode loop captured the per-layer graphs without decode buffers, so
Llama2_ fell back to x = x.clone() and every replay read the address of the
first step after it had been freed. The output was garbage audio codes with no
error: the decoded track is NaN, saved as a constant -32768 by the FLAC encoder.

YuE2 and the generic generate() already pin the hidden state and rotary tensors
through decode_buffers; do the same here, gated the way generate() gates it.

Fixes #16002 (the silent-noise report) and #16222.

2026-09-20 11:02:00 -04:00

..

audio_encoders

Lower the pos embed precision of SheetSage2 to match upstream. (#16395)

2026-09-17 23:43:08 -04:00

background_removal

Make a context manager for cast_bias_weight and use it. (#14750)

2026-08-08 22:38:34 -04:00

cldm

Add better error message for common error. (#10846)

2025-11-23 04:55:22 -05:00

comfy_types

Remove useless annotations imports. (#14105)

2026-05-25 19:23:29 -07:00

extra_samplers

Uni pc sampler now works with audio and video models.

2025-01-18 05:27:58 -05:00

image_encoders

feat: Support Sam3d-body (CORE-35) (#14370)

2026-08-22 22:08:22 -04:00

k_diffusion

Add cfgpp_ud10_ab sampler. (#15951)

2026-08-28 15:33:18 -04:00

ldm

Fix MiniMax Music 3 producing noise with CUDA graphs enabled. (#16428)

2026-09-20 11:02:00 -04:00

sd1_tokenizer

Silence clip tokenizer warning. (#8934)

2025-07-16 14:42:07 -04:00

t2i_adapter

Controlnet refactor.

2024-06-27 18:43:11 -04:00

taesd

Add support for taeh3. (#15695)

2026-08-17 23:20:28 -04:00

text_encoders

feat: Qwen-image 2.1 support (CORE-423) (#16400)

2026-09-19 18:44:02 -04:00

weight_adapter

MPDynamic: force load flux img_in weight (Fixes flux1 canny+depth lora crash) (#12446)

2026-02-15 20:30:09 -05:00

bg_removal_model.py

Fix background removal mask output shape (#14171)

2026-05-29 09:14:32 -07:00

cli_args.py

Add --disable-fast-disk to disable fast disk. (#16424)

2026-09-20 03:35:58 -04:00

clip_config_bigg.json

Fix potential issue with non clip text embeddings.

2024-07-30 14:41:13 -04:00

clip_model.py

Fix some clip vision regression. (#15506)

2026-08-11 15:54:15 -04:00

clip_vision_config_g.json

Add support for clip g vision model to CLIPVisionLoader.

2023-08-18 11:13:29 -04:00

clip_vision_config_h.json

Add support for unCLIP SD2.x models.

2023-04-01 23:19:15 -04:00

clip_vision_config_vitl_336_llava.json

Support llava clip vision model.

2025-03-06 00:24:43 -05:00

clip_vision_config_vitl_336.json

support clip-vit-large-patch14-336 (#4042)

2024-07-17 13:12:50 -04:00

clip_vision_config_vitl.json

Add support for unCLIP SD2.x models.

2023-04-01 23:19:15 -04:00

clip_vision_siglip2_base_naflex.json

Support the siglip 2 naflex model as a clip vision model. (#11831)

2026-01-12 17:05:54 -05:00

clip_vision_siglip_384.json

Support new flux model variants.

2024-11-21 08:38:23 -05:00

clip_vision_siglip_512.json

Support 512 siglip model.

2025-04-05 07:01:01 -04:00

clip_vision.py

feat: Support Pixal3d and TRELLIS2 (CORE-278) (CORE-199) (CORE-236) (CORE-312) (#14718)

2026-08-21 20:32:25 -04:00

comfy_api_env.py

feat: allow --comfy-api-base target ephemeral testenvs (#14569)

2026-07-08 23:20:10 -07:00

conds.py

Cleanups to the last PR. (#12646)

2026-02-26 01:30:31 -05:00

context_windows.py

feat: Context Windows sampling with LTX2 models and IC-LoRa guides (CORE-3) (#13325)

2026-06-20 07:47:31 +08:00

controlnet.py

Disable int8 weight-only quantization on devices without torch._int_mm (fixes MPS crash) (#16130)

2026-09-07 16:41:32 -04:00

deploy_environment.py

Add deploy environment header (Comfy-Env) to partner node API calls (#13425)

2026-05-04 20:17:56 -07:00

diffusers_convert.py

Remove useless code.

2025-01-24 06:15:54 -05:00

diffusers_load.py

load_unet -> load_diffusion_model with a model_options argument.

2024-08-12 23:20:57 -04:00

float.py

float: use CK stochastic rounding cuda kernel (#13971)

2026-05-28 19:23:42 -07:00

gligen.py

Remove some useless code. (#8812)

2025-07-06 07:07:39 -04:00

hooks.py

Fix typos (#10986)

2026-05-08 17:14:45 +08:00

internal_logging.py

rename comfy/logging.py to comfy/internal_logging.py (#15231)

2026-08-02 16:20:27 -04:00

latent_formats.py

feat: Qwen-image 2.1 support (CORE-423) (#16400)

2026-09-19 18:44:02 -04:00

lora_convert.py

Use torch RMSNorm for flux models and refactor hunyuan video code. (#12432)

2026-02-13 15:35:13 -05:00

lora.py

feat: Qwen-image 2.1 support (CORE-423) (#16400)

2026-09-19 18:44:02 -04:00

memory_management.py

Threaded Loader performance fixes / improvements (+ Aimdo 0.4.6) (#14116)

2026-05-30 15:20:04 -04:00

model_base.py

feat: Qwen-image 2.1 support (CORE-423) (#16400)

2026-09-19 18:44:02 -04:00

model_detection.py

feat: Qwen-image 2.1 support (CORE-423) (#16400)

2026-09-19 18:44:02 -04:00

model_management.py

Always put text encoder on GPU when dynamic vram on. (#16374)

2026-09-16 22:27:39 -04:00

model_patcher.py

Add --disable-fast-disk to disable fast disk. (#16424)

2026-09-20 03:35:58 -04:00

model_prefetch.py

Qwen3/3.5/3.8 cudagraphs and w4a8 gemv support (CORE-390) (#15623)

2026-09-17 20:38:24 -04:00

model_sampling.py

feat: Marigold v2 support (CORE-431) (#16232)

2026-09-11 15:40:56 -07:00

multigpu.py

Comfy Aimdo 0.5.3 + Memory compiler fixes (#16180)

2026-09-08 12:32:43 -04:00

nested_tensor.py

Make it easier to debug nested tensors. (#15383)

2026-08-07 22:14:04 -04:00

ops.py

Aimdo 0.5.5 + Auto-detect and enable --fast-disk when the disk is fast (CORE-440) (#16333)

2026-09-15 17:30:01 -04:00

options.py

Only parse command line args when main.py is called.

2023-09-13 11:38:20 -04:00

patcher_extension.py

Remove useless annotations imports. (#14105)

2026-05-25 19:23:29 -07:00

pinned_memory.py

Aimdo 0.5.5 + Auto-detect and enable --fast-disk when the disk is fast (CORE-440) (#16333)

2026-09-15 17:30:01 -04:00

pixel_space_convert.py

Changes to the previous radiance commit. (#9851)

2025-09-13 18:03:34 -04:00

quant_ops.py

quant_ops: drop the dead ROCm triton arch gate (#16211)

2026-09-09 16:14:27 -04:00

rmsnorm.py

feat: Gemma4 text generation support (CORE-30) (#13376)

2026-05-02 22:46:15 -04:00

sample.py

Allow regular single image Empty Latent Image node to be used with H3. (#15677)

2026-08-16 21:34:39 -04:00

sampler_helpers.py

MultiGPU Work Units For Accelerated Sampling (CORE-184) (#7063)

2026-05-25 18:26:40 -07:00

samplers.py

Add cfgpp_ud10_ab sampler. (#15951)

2026-08-28 15:33:18 -04:00

sd1_clip_config.json

Fix potential issue with non clip text embeddings.

2024-07-30 14:41:13 -04:00

sd1_clip.py

Qwen3/3.5/3.8 cudagraphs and w4a8 gemv support (CORE-390) (#15623)

2026-09-17 20:38:24 -04:00

sd.py

feat: Qwen-image 2.1 support (CORE-423) (#16400)

2026-09-19 18:44:02 -04:00

sdxl_clip.py

Add a T5TokenizerOptions node to set options for the T5 tokenizer. (#7803)

2025-04-25 19:36:00 -04:00

storage.py

Add --disable-fast-disk to disable fast disk. (#16424)

2026-09-20 03:35:58 -04:00

supported_models_base.py

Add SeedVR2 support (CORE-6) (#14424)

2026-07-10 15:07:42 +08:00

supported_models.py

feat: Qwen-image 2.1 support (CORE-423) (#16400)

2026-09-19 18:44:02 -04:00

system_memory.py

fix(memory): respect the container cgroup memory limit instead of host RAM (#15927)

2026-08-27 07:57:31 -07:00

utils.py

Aimdo 0.5.5 + Auto-detect and enable --fast-disk when the disk is fast (CORE-440) (#16333)

2026-09-15 17:30:01 -04:00