Commit Graph

  • c0c9720d77 Fix stable release workflow not pulling latest comfy kitchen. (#11695) comfyanonymous 2026-01-07 01:48:28 -08:00
  • fc0cb10bcb ComfyUI v0.8.0 v0.8.0 comfyanonymous 2026-01-07 04:07:31 -05:00
  • b7d7cc1d49 Fix fp8 fast issue. (#11688) comfyanonymous 2026-01-06 22:39:06 -08:00
  • 79e94544bd feat(api-nodes): add WAN2.6 ReferenceToVideo (#11644) Alexander Piskun 2026-01-07 08:04:50 +02:00
  • ce0000c4f2 Force sequential execution in CI test jobs (#11687) Yoland Yan 2026-01-06 21:57:31 -08:00
  • c5cfb34c07 Update comfy-kitchen version to 0.2.3 (#11685) comfyanonymous 2026-01-06 20:51:45 -08:00
  • edee33f55e Disable comfy kitchen cuda if pytorch cuda less than 13 (#11681) comfyanonymous 2026-01-06 19:13:43 -08:00
  • 2c03884f5f Skip fp4 matrix mult on devices that don't support it. (#11677) comfyanonymous 2026-01-06 15:07:26 -08:00
  • 6e9ee55cdd Disable ltxav previews. (#11676) comfyanonymous 2026-01-06 14:41:27 -08:00
  • 023cf13721 Fix lowvram issue with ltxv2 text encoder. (#11675) comfyanonymous 2026-01-06 14:33:03 -08:00
  • c3566c0d76 chore: update workflow templates to v0.7.67 (#11667) ComfyUI Wiki 2026-01-07 06:28:29 +08:00
  • c3c3e93c5b Use rope functions from comfy kitchen. (#11674) comfyanonymous 2026-01-06 13:57:50 -08:00
  • 6ffc159bdd Update comfy-kitchen version to 0.2.1 (#11672) comfyanonymous 2026-01-06 12:53:43 -08:00
  • 96e0d0924e Add helpful message to portable. (#11671) comfyanonymous 2026-01-06 11:43:24 -08:00
  • e14f3b6610 chore: update workflow templates to v0.7.66 (#11652) ComfyUI Wiki 2026-01-06 14:37:11 +08:00
  • 1618002411 Revert "Use rope functions from comfy kitchen. (#11647)" (#11648) comfyanonymous 2026-01-05 20:07:39 -08:00
  • 6ef85c4915 Use rope functions from comfy kitchen. (#11647) comfyanonymous 2026-01-05 19:50:35 -08:00
  • 6da00dd899 Initial ops changes to use comfy_kitchen: Initial nvfp4 checkpoint support. (#11635) comfyanonymous 2026-01-05 18:48:58 -08:00
  • 4f3f9e72a9 Fix name. (#11638) comfyanonymous 2026-01-05 02:41:23 -08:00
  • d157c3299d Refactor module_size function. (#11637) comfyanonymous 2026-01-05 00:48:31 -08:00
  • d1b9822f74 Add LTXAVTextEncoderLoader node. (#11634) comfyanonymous 2026-01-04 23:27:31 -08:00
  • f2b002372b Support the LTXV 2 model. (#11632) comfyanonymous 2026-01-04 22:58:59 -08:00
  • 38d0493825 Fix case where upscale model wouldn't be moved to cpu. (#11633) comfyanonymous 2026-01-04 16:13:50 -08:00
  • acbf08cd60 feat(api-nodes): add support for 720p resolution for Kling Omni nodes (#11604) Alexander Piskun 2026-01-04 09:05:02 +02:00
  • 53e762a3af Print memory summary on OOM to help with debugging. (#11613) comfyanonymous 2026-01-03 19:28:38 -08:00
  • 9a552df898 Remove leftover scaled_fp8 key. (#11603) comfyanonymous 2026-01-02 17:28:10 -08:00
  • f2fda021ab Tripo3D: pass face_limit parameter only when it differs from default (#11601) Alexander Piskun 2026-01-02 13:18:43 +02:00
  • 303b1735f8 Give Mahiro CFG a more appropriate display name (#11580) throttlekitty 2026-01-02 01:37:37 -07:00
  • 9e5f677746 Ignore all frames except the first one for MPO format. (#11569) Alexander Piskun 2026-01-02 10:35:34 +02:00
  • 65cfcf5b1b New Year ruff cleanup. (#11595) comfyanonymous 2026-01-01 19:06:14 -08:00
  • 1bdc9a947f Remove duplicate import of model_management (#11587) comfyanonymous 2025-12-31 16:29:55 -08:00
  • d622a61874 Refactor: move clip_preprocess to comfy.clip_model (#11586) comfyanonymous 2025-12-31 14:38:36 -08:00
  • 236b9e211d chore: update workflow templates to v0.7.65 (#11579) ComfyUI Wiki 2026-01-01 05:38:39 +08:00
  • 6ca3d5c011 fix(api-nodes-vidu): preserve percent-encoding for signed URLs (#11564) Alexander Piskun 2025-12-31 06:12:38 +02:00
  • 0be8a76c93 V3 Improvements + DynamicCombo + Autogrow exposed in public API (#11345) Jedrzej Kosinski 2025-12-30 20:09:55 -08:00
  • 0357ed7ec4 Add support for sage attention 3 in comfyui, enable via new cli arg (#11026) mengqin 2025-12-30 17:53:52 -10:00
  • f59f71cf34 ComfyUI version v0.7.0 v0.7.0 comfyanonymous 2025-12-30 22:41:22 -05:00
  • 178bdc5e14 Add handling for vace_context in context windows (#11386) drozbay 2025-12-30 15:40:42 -07:00
  • 25a1bfab4e chore(api-nodes-bytedance): mark "seededit" as deprecated, adjust display name of Seedream (#11490) Alexander Piskun 2025-12-30 18:33:34 +02:00
  • d7111e426a ResizeByLongerSide: support video (#11555) Tavi Halperin 2025-12-30 03:07:29 +02:00
  • 0e6221cc79 Add some warnings for pin and unpin errors. (#11561) comfyanonymous 2025-12-29 15:26:42 -08:00
  • 9ca7e143af mm: discard async errors from pinning failures (#10738) rattus 2025-12-29 15:19:34 -08:00
  • 8fd07170f1 Comment out unused norm_final in lumina/z image model. (#11545) comfyanonymous 2025-12-28 19:07:25 -08:00
  • 2943093a53 Enable async offload by default for AMD. (#11534) comfyanonymous 2025-12-27 15:54:15 -08:00
  • 36deef2c57 chore(api-nodes): switch to credits instead of $ (#11489) Alexander Piskun 2025-12-27 05:56:52 +02:00
  • 0d2e4bdd44 fix(api-nodes-gemini): always force enhance_prompt to be True (#11503) Alexander Piskun 2025-12-27 05:55:30 +02:00
  • eff4ea0b62 [V3] converted nodes_images.py to V3 schema (#11206) Alexander Piskun 2025-12-27 05:39:02 +02:00
  • 865568b7fc feat(api-nodes): add Kling Motion Control node (#11493) Alexander Piskun 2025-12-27 05:16:21 +02:00
  • 1e4e342f54 Fix noise with ancestral samplers when inferencing on cpu. (#11528) comfyanonymous 2025-12-26 19:03:01 -08:00
  • 16fb6849d2 bump comfyui_manager version to the 4.0.4 (#11521) Dr.Lt.Data 2025-12-27 08:55:59 +09:00
  • d9a76cf66e Specify in readme that we only support pytorch 2.4 and up. (#11512) comfyanonymous 2025-12-25 20:46:51 -08:00
  • 532e285079 Add a ManualSigmas node. (#11499) comfyanonymous 2025-12-24 16:09:37 -08:00
  • 4f067b07fb chore: update workflow templates to v0.7.64 (#11496) ComfyUI Wiki 2025-12-25 07:54:21 +08:00
  • 650e716dda Bump comfyui-frontend-package to 1.35.9 (#11470) Comfy Org PR Bot 2025-12-24 14:29:41 +09:00
  • e4c61d7555 ComfyUI v0.6.0 v0.6.0 comfyanonymous 2025-12-23 20:50:02 -05:00
  • 22ff1bbfcb chore: update workflow templates to v0.7.63 (#11482) ComfyUI Wiki 2025-12-24 09:48:45 +08:00
  • f4f44bb807 api-nodes: use new custom endpoint for Nano Banana (#11311) Alexander Piskun 2025-12-23 22:10:27 +02:00
  • 33aa808713 Make denoised output on custom sampler nodes work with nested tensors. (#11471) comfyanonymous 2025-12-22 13:43:24 -08:00
  • eb0e10aec4 Update workflow templates to v0.7.62 (#11467) ComfyUI Wiki 2025-12-23 05:02:41 +08:00
  • c176b214cc extend possible duration range for Kling O1 StartEndFrame node (#11451) Alexander Piskun 2025-12-22 08:44:49 +02:00
  • 91bf6b6aa3 Add node to create empty latents for qwen image layered model. (#11460) comfyanonymous 2025-12-21 16:59:40 -08:00
  • 807538fe6c Core release process. (#11447) comfyanonymous 2025-12-20 17:02:02 -08:00
  • bbb11e2608 fix(api-nodes): Topaz 4k video upscaling (#11438) Alexander Piskun 2025-12-20 18:48:28 +02:00
  • 0899012ad6 chore(api-nodes): by default set Watermark generation to False (#11437) Alexander Piskun 2025-12-20 08:24:37 +02:00
  • fb478f679a Only apply gemma quant config to gemma model for newbie. (#11436) comfyanonymous 2025-12-19 22:02:43 -08:00
  • 4c432c11ed Implement Jina CLIP v2 and NewBie dual CLIP (#11415) woctordho 2025-12-20 13:57:22 +08:00
  • 31e961736a Fix issue with batches and newbie. (#11435) comfyanonymous 2025-12-19 21:23:51 -08:00
  • 767ee30f21 ZImageFunControlNet: Fix mask concatenation in --gpu-only (#11421) rattus 2025-12-19 21:22:17 -08:00
  • 3ab9748903 Disable prompt weights on newbie te. (#11434) comfyanonymous 2025-12-19 21:19:47 -08:00
  • 0aa7fa464e Implement sliding attention in Gemma3 (#11409) woctordho 2025-12-20 13:16:46 +08:00
  • 514c24d756 Fix error from logging line (#11423) drozbay 2025-12-19 21:22:45 -07:00
  • 809ce68749 Support nested tensor denoise masks. (#11431) comfyanonymous 2025-12-19 16:59:25 -08:00
  • cc4ddba1b6 Allow enabling use of MIOpen by setting COMFYUI_ENABLE_MIOPEN=1 as an env var (#11366) BradPepersAMD 2025-12-19 15:01:50 -07:00
  • 8376ff6831 bump comfyui_manager version to the 4.0.3b7 (#11422) Dr.Lt.Data 2025-12-20 03:41:56 +09:00
  • 5b4d0664c8 add Flux2MaxImage API Node (#11420) Alexander Piskun 2025-12-19 20:02:49 +02:00
  • 894802b0f9 Add LatentCutToBatch node. (#11411) comfyanonymous 2025-12-18 19:21:40 -08:00
  • 28eaab608b Diffusion model part of Qwen Image Layered. (#11408) comfyanonymous 2025-12-18 17:21:14 -08:00
  • 6a2678ac65 Trim/pad channels in VAE code. (#11406) comfyanonymous 2025-12-18 15:22:38 -08:00
  • e4fb3a3572 Support loading Wan/Qwen VAEs with different in/out channels. (#11405) comfyanonymous 2025-12-18 14:45:33 -08:00
  • e8ebbe668e chore: update workflow templates to v0.7.60 (#11403) ComfyUI Wiki 2025-12-19 06:09:29 +08:00
  • 1ca89b810e Add unified jobs API with /api/jobs endpoints (#11054) ric-yu 2025-12-17 21:44:31 -08:00
  • bf7dc63bd6 skip_load_model -> force_full_load (#11390) comfyanonymous 2025-12-17 20:29:32 -08:00
  • 86dbb89fc9 Resolution bucketing and Trainer implementation refactoring (#11117) Kohaku-Blueleaf 2025-12-18 11:15:27 +08:00
  • ba6080bbab ComfyUI v0.5.1 v0.5.1 comfyanonymous 2025-12-17 21:04:50 -05:00
  • 16d85ea133 Better handle torch being imported by prestartup nodes. (#11383) comfyanonymous 2025-12-17 16:43:18 -08:00
  • 5d9ad0c6bf Fix the last step with non-zero sigma in sa_solver (#11380) chaObserv 2025-12-18 02:57:40 +08:00
  • c08f97f344 fix regression in V3 nodes processing (#11375) Alexander Piskun 2025-12-17 20:24:25 +02:00
  • 887143854b feat(api-nodes): add GPT-Image-1.5 (#11368) Alexander Piskun 2025-12-17 19:43:41 +02:00
  • 3a5f239cb6 ComfyUI v0.5.0 v0.5.0 comfyanonymous 2025-12-17 03:46:11 -05:00
  • 827bb1512b Add exp_heun_2_x0 sampler series (#11360) chaObserv 2025-12-17 12:35:43 +08:00
  • ffdd53b327 Check state dict key to auto enable the index_timestep_zero ref method. (#11362) comfyanonymous 2025-12-16 14:03:17 -08:00
  • 65e2103b09 feat(api-nodes): add Wan2.6 model to video nodes (#11357) Alexander Piskun 2025-12-16 23:51:48 +02:00
  • 9304e47351 Update workflows for new release process (#11064) Benjamin Lu 2025-12-15 23:24:18 -08:00
  • bc606d7d64 Add a way to set the default ref method in the qwen image code. (#11349) comfyanonymous 2025-12-15 22:26:55 -08:00
  • 645ee1881e Inpainting for z image fun control. Use the ZImageFunControlnet node. (#11346) comfyanonymous 2025-12-15 20:38:12 -08:00
  • 3d082c3206 bump comfyui-frontend-package to 1.34.9 (patch) (#11342) Christian Byrne 2025-12-15 20:35:37 -08:00
  • 683569de55 Only enable fp16 on ZImage on newer pytorch. (#11344) comfyanonymous 2025-12-15 19:33:27 -08:00
  • ea2c117bc3 [BlockInfo] Wan (#10845) Haoming 2025-12-16 09:59:16 +08:00
  • fc4af86068 [BlockInfo] Lumina (#11227) Haoming 2025-12-16 09:57:28 +08:00
  • 41bcf0619d Add code to detect if a z image fun controlnet is broken or not. (#11341) comfyanonymous 2025-12-15 17:51:06 -08:00