Commit Graph

  • e9364ee279 Turn on TORCH_ROCM_AOTRITON_ENABLE_EXPERIMENTAL by default. (#10168) comfyanonymous 2025-10-02 14:57:15 -07:00
  • f6e3e9a456 fix(api-nodes): made logging path to be smaller (#10156) Alexander Piskun 2025-10-03 00:50:31 +03:00
  • 8f4ee9984c convert nodes_morphology.py to V3 schema (#10159) Alexander Piskun 2025-10-02 23:53:00 +03:00
  • 0e9d1724be Add a .bat to the AMD portable to disable smart memory. (#10153) comfyanonymous 2025-10-01 21:33:05 -07:00
  • 4965c0e2ac WAN: Fix cache VRAM leak on error (#10141) rattus128 2025-10-02 08:42:16 +10:00
  • 911331c06c sd: fix VAE tiled fallback VRAM leak (#10139) rattus128 2025-10-02 08:40:28 +10:00
  • bb32d4ec31 feat: Add Epsilon Scaling node for exposure bias correction (#10132) Koratahiu 2025-10-02 00:59:07 +03:00
  • a6f83a4a1a Support the new hunyuan vae. (#10150) comfyanonymous 2025-10-01 14:19:13 -07:00
  • e4f99b479a convert nodes_ip2p.pt to V3 schema (#10097) Alexander Piskun 2025-10-01 22:20:30 +03:00
  • d9c0a4053d convert nodes_lt.py to V3 schema (#10084) Alexander Piskun 2025-10-01 22:19:56 +03:00
  • 11bab7be76 convert nodes_pag.py to V3 schema (#10080) Alexander Piskun 2025-10-01 22:18:49 +03:00
  • 3af1881455 convert nodes_optimalsteps.py to V3 schema (#10074) Alexander Piskun 2025-10-01 22:18:04 +03:00
  • e0210ce0a7 convert nodes_differential_diffusion.py to V3 schema (#10056) Alexander Piskun 2025-10-01 22:17:33 +03:00
  • 7eb7160db4 convert nodes_gits.py to V3 schema (#9949) Alexander Piskun 2025-10-01 22:16:59 +03:00
  • 638097829d convert nodes_audio_encoder.py to V3 schema (#10123) Alexander Piskun 2025-10-01 09:00:22 +03:00
  • c4a8cf60ab Bump frontend to 1.27.7 (#10133) AustinMroz 2025-09-30 22:12:32 -07:00
  • bab8ba20bf ComfyUI version 0.3.62. v0.3.62 comfyanonymous 2025-09-30 15:12:07 -04:00
  • b682a73c55 enable Seedance Pro model in the FirstLastFrame node (#10120) Alexander Piskun 2025-09-30 20:43:41 +03:00
  • 631b9ae861 fix(Rodin3D-Gen2): missing "task_uuid" parameter (#10128) Alexander Piskun 2025-09-30 20:21:47 +03:00
  • f48d7230de Add new portable links to readme. (#10112) comfyanonymous 2025-09-30 09:17:49 -07:00
  • 6e079abc3a Workflow permission fix. (#10110) comfyanonymous 2025-09-29 20:11:37 -07:00
  • 977a4ed8c5 ComfyUI version 0.3.61 v0.3.61 comfyanonymous 2025-09-29 23:04:42 -04:00
  • 414a178fb6 Add basic readme for AMD portable. (#10109) comfyanonymous 2025-09-29 20:03:02 -07:00
  • 447884b657 Make stable release workflow callable. (#10108) comfyanonymous 2025-09-29 17:37:51 -07:00
  • bed4b49d08 Add action to do the full stable release. (#10107) comfyanonymous 2025-09-29 17:31:15 -07:00
  • 342cf644ce Add a way to have different names for stable nvidia portables. (#10106) comfyanonymous 2025-09-29 17:05:44 -07:00
  • 3758848423 Different base files for nvidia and amd portables. (#10105) comfyanonymous 2025-09-29 16:54:37 -07:00
  • 0db6aabed3 Different base files for different release. (#10104) comfyanonymous 2025-09-29 16:54:05 -07:00
  • 1673ace19b Make the final release test optional in the stable release action. (#10103) comfyanonymous 2025-09-29 16:08:42 -07:00
  • 7f38e4c538 Add action to create cached deps with manually specified torch. (#10102) comfyanonymous 2025-09-29 14:27:52 -07:00
  • 8accf50908 convert nodes_mahiro.py to V3 schema (#10070) Alexander Piskun 2025-09-29 22:35:51 +03:00
  • ed0f4a609b dont cache new locale entry points (#10101) Christian Byrne 2025-09-29 12:16:02 -07:00
  • 041b8824f5 convert nodes_perpneg.py to V3 schema (#10081) Alexander Piskun 2025-09-29 22:05:28 +03:00
  • b1111c2062 convert nodes_mochi.py to V3 schema (#10069) Alexander Piskun 2025-09-29 22:03:35 +03:00
  • 05a258efd8 add WanImageToImageApi node (#10094) Alexander Piskun 2025-09-29 22:01:04 +03:00
  • c8276f8c6b Update template to 0.1.91 (#10096) ComfyUI Wiki 2025-09-30 02:59:42 +08:00
  • 6ec1cfe101 [Rodin3d api nodes] Updated the name of the save file path (changed from timestamp to UUID). (#10011) Changrz 2025-09-30 02:59:12 +08:00
  • b60dc31627 Update command to install latest nighly pytorch. (#10085) comfyanonymous 2025-09-28 10:41:32 -07:00
  • 555f902fc1 Fix stable workflow creating multiple draft releases. (#10067) comfyanonymous 2025-09-27 19:43:25 -07:00
  • 1364548c72 feat: ComfyUI can be run on the specified Ascend NPU (#9663) Rui Wang (王瑞) 2025-09-28 10:36:02 +08:00
  • 2dadb34860 convert nodes_hypertile.py to V3 schema (#10061) Alexander Piskun 2025-09-28 05:16:22 +03:00
  • 1cf86f5ae5 convert nodes_lumina2.py to V3 schema (#10058) Alexander Piskun 2025-09-28 05:12:51 +03:00
  • a1127b232d convert nodes_lotus.py to V3 schema (#10057) Alexander Piskun 2025-09-28 05:11:36 +03:00
  • 896f2e653c Fix typo in release workflow. (#10066) comfyanonymous 2025-09-27 18:30:35 -07:00
  • 40ae495ddc Improvements to the stable release workflow. (#10065) comfyanonymous 2025-09-27 17:28:49 -07:00
  • 653ceab414 Reduce Peak WAN inference VRAM usage - part II (#10062) rattus128 2025-09-28 08:14:16 +10:00
  • 160698eb41 convert nodes_qwen.py to V3 schema (#10049) Alexander Piskun 2025-09-27 22:25:35 +03:00
  • 7eca95657c convert nodes_photomaker.py to V3 schema (#10017) Alexander Piskun 2025-09-27 12:36:43 +03:00
  • ad5aef2d0c convert nodes_pixart.py to V3 schema (#10019) Alexander Piskun 2025-09-27 12:34:32 +03:00
  • bcfd80dd79 convert nodes_luma.py to V3 schema (#10030) Alexander Piskun 2025-09-27 12:28:11 +03:00
  • 6b4b671ce7 convert nodes_bfl.py to V3 schema (#10033) Alexander Piskun 2025-09-27 12:27:01 +03:00
  • a9cf1cd249 convert nodes_hidream.py to V3 schema (#9946) Alexander Piskun 2025-09-27 09:13:05 +03:00
  • 255572188f Add workflow templates version tracking to system_stats (#9089) Christian Byrne 2025-09-26 21:29:13 -07:00
  • 0572029fee Update template to 0.1.88 (#10046) ComfyUI Wiki 2025-09-27 12:18:16 +08:00
  • 196954ab8c Add 'input_cond' and 'input_uncond' to the args dictionary passed into sampler_cfg_function (#10044) Jedrzej Kosinski 2025-09-26 19:55:03 -07:00
  • 1e098d6132 Don't add template to qwen2.5vl when template is in prompt. (#10043) comfyanonymous 2025-09-26 15:34:17 -07:00
  • cd66d72b46 convert CLIPTextEncodeSDXL nodes to V3 schema (#9716) Alexander Piskun 2025-09-27 00:15:44 +03:00
  • 2103e39335 convert nodes_post_processing to V3 schema (#9491) Alexander Piskun 2025-09-27 00:14:42 +03:00
  • d20576e6a3 convert nodes_sag.py to V3 schema (#9940) Alexander Piskun 2025-09-27 00:13:52 +03:00
  • a061b06321 convert nodes_tcfg.py to V3 schema (#9942) Alexander Piskun 2025-09-27 00:13:05 +03:00
  • 80718908a9 convert nodes_sdupscale.py to V3 schema (#9943) Alexander Piskun 2025-09-27 00:12:38 +03:00
  • 7ea173c187 convert nodes_fresca.py to V3 schema (#9951) Alexander Piskun 2025-09-27 00:12:04 +03:00
  • 76eb1d72c3 convert nodes_rebatch.py to V3 schema (#9945) Alexander Piskun 2025-09-27 00:10:49 +03:00
  • c4a46e943c Add @kosinkadink as code owner (#10041) Yoland Yan 2025-09-26 14:08:16 -07:00
  • 2b7f9a8196 Fix the failing unit test. (#10037) comfyanonymous 2025-09-26 11:12:43 -07:00
  • ce4cb2389c Make LatentCompositeMasked work with basic video latents. (#10023) comfyanonymous 2025-09-25 14:20:13 -07:00
  • c8d2117f02 Fix memory leak by properly detaching model finalizer (#9979) Guy Niv 2025-09-25 05:35:12 +03:00
  • fccab99ec0 Fix issue with .view() in HuMo. (#10014) comfyanonymous 2025-09-24 17:09:42 -07:00
  • fd79d32f38 Add new audio nodes (#9908) Jukka Seppänen 2025-09-25 01:59:29 +03:00
  • 341b4adefd Rodin3D - add [Rodin3D Gen-2 generate] api-node (#9994) Changrz 2025-09-25 02:05:37 +08:00
  • b8730510db ComfyUI version 0.3.60 v0.3.60 comfyanonymous 2025-09-23 11:50:33 -04:00
  • e808790799 feat(api-nodes): add wan t2i, t2v, i2v nodes (#9996) Alexander Piskun 2025-09-23 18:36:47 +03:00
  • 145b0e4f79 update template to 0.1.86 (#9998) ComfyUI Wiki 2025-09-23 23:22:35 +08:00
  • 707b2638ec Fix bug with WanAnimateToVideo. (#9990) comfyanonymous 2025-09-22 14:34:33 -07:00
  • 8a5ac527e6 Fix bug with WanAnimateToVideo node. (#9988) comfyanonymous 2025-09-22 14:26:58 -07:00
  • e3206351b0 add offset param (#9977) Christian Byrne 2025-09-22 14:12:32 -07:00
  • 1fee8827cb Support for qwen edit plus model. Use the new TextEncodeQwenImageEditPlus. (#9986) comfyanonymous 2025-09-22 13:49:48 -07:00
  • 27bc181c49 Set some wan nodes as no longer experimental. (#9976) comfyanonymous 2025-09-21 16:48:31 -07:00
  • d1d9eb94b1 Lower wan memory estimation value a bit. (#9964) comfyanonymous 2025-09-20 19:09:35 -07:00
  • 7be2b49b6b Fix LoRA Trainer bugs with FP8 models. (#9854) Kohaku-Blueleaf 2025-09-21 09:24:48 +08:00
  • 9ed3c5cc09 [Reviving #5709] Add strength input to Differential Diffusion (#9957) Jedrzej Kosinski 2025-09-20 18:10:39 -07:00
  • 66241cef31 Add inputs for character replacement to the WanAnimateToVideo node. (#9960) comfyanonymous 2025-09-19 23:24:10 -07:00
  • e8df53b764 Update WanAnimateToVideo to more easily extend videos. (#9959) comfyanonymous 2025-09-19 15:48:56 -07:00
  • 852704c81a fix(seedream4): add flag to ignore error on partial success (#9952) Alexander Piskun 2025-09-19 23:04:51 +03:00
  • 9fdf8c25ab api_nodes: reduce default timeout from 7 days to 2 hours (#9918) Alexander Piskun 2025-09-19 23:02:43 +03:00
  • dc95b6acc0 Basic WIP support for the wan animate model. (#9939) comfyanonymous 2025-09-19 00:07:17 -07:00
  • 711bcf33ee Bump frontend to 1.26.13 (#9933) Christian Byrne 2025-09-19 00:03:30 -07:00
  • 24b0fce099 Do padding of audio embed in model for humo for more flexibility. (#9935) comfyanonymous 2025-09-18 16:54:16 -07:00
  • 1ea8c54064 make kernel of same type as image to avoid mismatch issues (#9932) Jodh Singh 2025-09-18 19:51:16 -04:00
  • 8d6653fca6 Enable fp8 ops by default on gfx1200 (#9926) DELUXA 2025-09-19 02:50:37 +03:00
  • dd611a7700 Support the HuMo 17B model. (#9912) comfyanonymous 2025-09-17 15:39:24 -07:00
  • 9288c78fc5 Support the HuMo model. (#9903) comfyanonymous 2025-09-16 21:12:48 -07:00
  • e42682b24e Reduce Peak WAN inference VRAM usage (#9898) rattus128 2025-09-17 09:21:14 +10:00
  • a39ac59c3e Add encoder part of whisper large v3 as an audio encoder model. (#9894) comfyanonymous 2025-09-15 22:19:50 -07:00
  • 1a85483da1 Fix depending on asserts to raise an exception in BatchedBrownianTree and Flash attn module (#9884) blepping 2025-09-15 18:05:03 -06:00
  • 47a9cde5d3 Support the omnigen2 umo lora. (#9886) comfyanonymous 2025-09-15 15:10:55 -07:00
  • 4f1f26ac6c Add that hunyuan image is supported to readme. (#9857) comfyanonymous 2025-09-14 01:05:38 -07:00
  • f228367c5e Make ModuleNotFoundError ImportError instead (#9850) Jedrzej Kosinski 2025-09-13 18:34:21 -07:00
  • 80b7c9455b Changes to the previous radiance commit. (#9851) comfyanonymous 2025-09-13 15:03:34 -07:00
  • c1297f4eb3 Add support for Chroma Radiance (#9682) blepping 2025-09-13 15:58:43 -06:00