Dima/ComfyUI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Commit Graph

  • 5f41584e96 Disable dynamic_vram when weight hooks applied (#12653) rattus 2026-02-28 13:50:18 -08:00
  • 1f6744162f feat: Support SCAIL WanVideo model (#12614) Jukka Seppänen 2026-02-28 23:49:12 +02:00
  • 95e1059661 fix(ace15): handle missing lm_metadata in memory estimation during checkpoint export #12669 (#12686) fappaz 2026-02-28 19:18:40 +13:00
  • 80d49441e5 refactor: use AspectRatio enum members as ASPECT_RATIOS dict keys (#12689) Christian Byrne 2026-02-27 20:53:46 -08:00
  • 9d0e114ee3 PyOpenGL-accelerate is not necessary. (#12692) comfyanonymous 2026-02-27 20:34:58 -08:00
  • ac4412d0fa Native LongCat-Image implementation (#12597) Talmaj 2026-02-28 05:04:34 +01:00
  • 94f1a1cc9d Limit overlap in image tile and combine nodes to prevent issues. (#12688) comfyanonymous 2026-02-27 17:16:24 -08:00
  • e721e24136 ops: implement lora requanting for non QuantizedTensor fp8 (#12668) rattus 2026-02-27 16:05:51 -08:00
  • 25ec3d96a3 Class WanVAE, def encode, feat_map is using self.decoder instead of self.encoder (#12682) Reiner "Tiles" Prokein 2026-02-28 01:03:45 +01:00
  • 1f1ec377ce feat: add ResolutionSelector node for aspect ratio and megapixel-based resolution calculation (#12199) Christian Byrne 2026-02-27 09:13:57 -08:00
  • 0a7f8e11b6 fix torch.cat requiring inputs to all be same dimensions (#12673) pythongosssss 2026-02-27 16:13:24 +00:00
  • 35e9fce775 Enable Pytorch Attention for gfx950 (#12641) vickytsang 2026-02-26 17:16:12 -08:00
  • c7f7d52b68 feat: Support SDPose-OOD (#12661) Jukka Seppänen 2026-02-27 02:59:05 +02:00
  • 08b26ed7c2 bug_report template: Push harder for logs (#12657) rattus 2026-02-26 15:59:24 -08:00
  • b233dbe0bc feat(ace-step): add ACE-Step 1.5 lycoris key alias mapping for LoKR #12638 (#12665) fappaz 2026-02-27 12:19:19 +13:00
  • 3811780e4f Portable with cu128 isn't useful anymore. (#12666) comfyanonymous 2026-02-26 14:12:29 -08:00
  • 3dd10a59c0 ComfyUI v0.15.1 v0.15.1 comfyanonymous 2026-02-26 15:59:22 -05:00
  • 88d05fe483 chore: update workflow templates to v0.9.4 (#12664) ComfyUI Wiki 2026-02-27 04:52:45 +08:00
  • fd41ec97cc feat(api-nodes): add NanoBanana2 (#12660) Alexander Piskun 2026-02-26 22:52:10 +02:00
  • 420e900f69 main: load aimdo earlier (#12655) rattus 2026-02-26 12:19:38 -08:00
  • 38ca94599f pyopengl-accelerate can cause object to be numpy ints instead of bare ints, which the glDeleteTextures function does not accept, explicitly cast to int (#12650) pythongosssss 2026-02-26 11:07:35 +00:00
  • 74b5a337dc fix: move essentials_category to correct replacement nodes (#12568) Christian Byrne 2026-02-26 01:00:32 -08:00
  • 8a4d85c708 Cleanups to the last PR. (#12646) comfyanonymous 2026-02-25 22:30:31 -08:00
  • a4522017c5 feat: per-guide attention strength control in self-attention (#12518) Tavi Halperin 2026-02-26 08:25:23 +02:00
  • 907e5dcbbf initial FlowRVS support (#12637) Jukka Seppänen 2026-02-26 06:38:46 +02:00
  • 7253531670 Fix ltxav te mem estimation. (#12643) comfyanonymous 2026-02-25 20:13:47 -08:00
  • e14b04478c Fix LTXAV text enc min length. (#12640) comfyanonymous 2026-02-25 19:36:02 -08:00
  • eb8737d675 Update requirements.txt (#12642) Christian Byrne 2026-02-25 18:30:48 -08:00
  • 0467f690a8 comfy aimdo 0.2.2 (#12635) rattus 2026-02-25 13:50:05 -08:00
  • 4f5b7dbf1f Fix Aimdo fallback on probe to not use zero-copy sft (#12634) rattus 2026-02-25 13:49:48 -08:00
  • 3ebe1ac22e Disable dynamic_vram when using torch compiler (#12612) rattus 2026-02-24 16:13:46 -08:00
  • befa83d434 comfy aimdo 0.2.1 (#12620) rattus 2026-02-24 13:02:26 -08:00
  • 33f83d53ae Fix KeyError when prompt entries lack class_type key (#12595) Jedrzej Kosinski 2026-02-24 13:02:05 -08:00
  • b874bd2b8c ComfyUI v0.15.0 v0.15.0 comfyanonymous 2026-02-24 12:37:16 -05:00
  • 0aa02453bb chore: update embedded docs to v0.4.3 (#12601) ComfyUI Wiki 2026-02-25 01:41:36 +08:00
  • 599f9c5010 Don't crash right away if op is uninitialized. (#12615) comfyanonymous 2026-02-24 09:28:25 -08:00
  • 11fefa58e9 chore: update workflow templates to v0.9.3 (#12610) ComfyUI Wiki 2026-02-25 01:04:51 +08:00
  • d8090013b8 feat(api-nodes): add ByteDance Seedream-5 model (#12609) Alexander Piskun 2026-02-24 19:03:30 +02:00
  • 048dd2f321 Patch frontend to 1.39.16 (from 1.39.14) (#12604) Christian Byrne 2026-02-24 00:44:40 -08:00
  • 84aba95e03 Temporality unbreak some LTXAV workflows to give people time to migrate. (#12605) comfyanonymous 2026-02-23 21:50:03 -08:00
  • 9b1c63eb69 Add SplitImageToTileList and ImageMergeTileList nodes. (#12599) comfyanonymous 2026-02-23 18:01:17 -08:00
  • 7a7debcaf1 chore: update workflow templates to v0.9.2 (#12596) ComfyUI Wiki 2026-02-24 07:27:20 +08:00
  • dba2766e53 feat(api-nodes): add KlingAvatar node (#12591) Alexander Piskun 2026-02-23 21:27:16 +02:00
  • caa43d2395 Fix issue loading fp8 ltxav checkpoints. (#12582) comfyanonymous 2026-02-22 13:00:02 -08:00
  • 07ca6852e8 Fix dtype issue in embeddings connector. (#12570) comfyanonymous 2026-02-22 00:18:20 -08:00
  • f266b8d352 Move LTXAV av embedding connectors to diffusion model. (#12569) comfyanonymous 2026-02-21 19:29:58 -08:00
  • b6cb30bab5 chore: tune CodeRabbit config to limit review scope and disable for drafts (#12567) Christian Byrne 2026-02-21 18:32:15 -08:00
  • ee72752162 Add category to Normalized Attention Guidance node (#12565) Christian Byrne 2026-02-21 16:51:21 -08:00
  • 7591d781a7 fix: specify UTF-8 encoding when reading subgraph files (#12563) Alexander Brown 2026-02-21 15:05:00 -08:00
  • 0bfb936ab4 comfy-aimdo 0.2 - Improved pytorch allocator integration (#12557) rattus 2026-02-21 10:52:57 -08:00
  • 602b2505a4 add support for pyopengl < 3.1.4 where the size parameter does not exist (#12555) pythongosssss 2026-02-21 14:14:57 +00:00
  • 04a55d5019 fix: swap essentials_category from CLIPTextEncode to PrimitiveStringMultiline (#12553) Christian Byrne 2026-02-20 23:46:46 -08:00
  • 5fb8f06495 feat: add essential subgraph blueprints (#12552) Christian Byrne 2026-02-20 23:40:13 -08:00
  • 5a182bfaf1 update glsl blueprint with gradient (#12548) Terry Jia 2026-02-21 02:02:36 -05:00
  • f394af8d0f feat: add gradient-slider display mode for FLOAT inputs (#12536) Terry Jia 2026-02-21 01:52:32 -05:00
  • aeb5bdc8f6 Fix non-contiguous audio waveform crash in video save (#12550) Arthur R Longbottom 2026-02-20 20:37:55 -08:00
  • 64953bda0a Update nightly installation command for ROCm (#12547) comfyanonymous 2026-02-20 18:32:05 -08:00
  • b254cecd03 chore: add CodeRabbit configuration for automated code review (#12539) Christian Byrne 2026-02-20 00:25:54 -08:00
  • 1bb956fb66 [API Nodes] add ElevenLabs nodes (#12207) Alexander Piskun 2026-02-20 08:12:28 +02:00
  • 96d6bd1a4a Add GLSL shader node using PyOpenGL (#12148) pythongosssss 2026-02-20 04:22:13 +00:00
  • 5f2117528a Force min length 1 when tokenizing for text generation. (#12538) comfyanonymous 2026-02-19 19:57:44 -08:00
  • 0301ccf745 Small cleanup and try to get qwen 3 work with the text gen. (#12537) comfyanonymous 2026-02-19 19:42:28 -08:00
  • 4d172e9ad7 feat: mark 429 widgets as advanced for collapsible UI (#12197) Christian Byrne 2026-02-19 19:20:02 -08:00
  • 5632b2df9d feat: add essentials_category (#12357) Yourz 2026-02-20 11:00:26 +08:00
  • 2687652530 fix(api-nodes): force Gemini to return uncompressed images (#12516) Alexander Piskun 2026-02-19 14:10:39 +02:00
  • 6d11cc7354 feat: Add basic text generation support with native models, initially supporting Gemma3 (#12392) Jukka Seppänen 2026-02-19 03:49:43 +02:00
  • f262444dd4 Add simple 3 band equalizer node for audio. (#12519) comfyanonymous 2026-02-18 15:36:35 -08:00
  • 239ddd3327 fix(api-nodes): add price badge for Rodin Gen-2 node (#12512) Alexander Piskun 2026-02-18 09:15:23 +02:00
  • 185c61dc26 fix: use glob matching for Gemini image MIME types (#12511) v0.14.2 origin/release/v0.14.2 Hunter 2026-02-18 00:03:54 -05:00
  • 83dd65f23a fix: use glob matching for Gemini image MIME types (#12511) Hunter 2026-02-18 00:03:54 -05:00
  • 8ad38d2073 BBox widget (#11594) Terry Jia 2026-02-17 20:13:39 -05:00
  • 6c14f129af Bump comfyui-frontend-package to 1.39.14 (#12494) Comfy Org PR Bot 2026-02-18 06:41:34 +09:00
  • 58dcc97dcf ops: limit return of requants (#12506) rattus 2026-02-17 12:32:27 -08:00
  • 19236edfa4 ComfyUI v0.14.1 v0.14.1 comfyanonymous 2026-02-17 13:28:06 -05:00
  • 73c3f86973 chore: update workflow templates to v0.8.43 (#12507) ComfyUI Wiki 2026-02-18 02:25:55 +08:00
  • 262abf437b feat(api-nodes): add Recraft V4 nodes (#12502) Alexander Piskun 2026-02-17 20:25:44 +02:00
  • 5284e6bf69 feat(api-nodes): add "viduq3-turbo" model and Vidu3StartEnd node; fix the price badges (#12482) Alexander Piskun 2026-02-17 20:07:14 +02:00
  • 44f8598521 Fix anima LLM adapter forward when manual cast (#12504) chaObserv 2026-02-17 23:56:44 +08:00
  • fe52843fe5 ComfyUI v0.14.0 v0.14.0 comfyanonymous 2026-02-17 00:39:54 -05:00
  • c39653163d Fix anima preprocess text embeds not using right inference dtype. (#12501) comfyanonymous 2026-02-16 21:29:20 -08:00
  • 18927538a1 Implement NAG on all the models based on the Flux code. (#12500) comfyanonymous 2026-02-16 20:30:34 -08:00
  • 8a6fbc2dc2 Allow control_after_generate to be type ControlAfterGenerate in v3 schema (#12187) Jedrzej Kosinski 2026-02-16 19:20:21 -08:00
  • b44fc4c589 add venv* to gitignore (#12431) Alex Butler 2026-02-17 03:16:19 +00:00
  • 4454fab7f0 Remove code to support RMSNorm on old pytorch. (#12499) comfyanonymous 2026-02-16 17:09:24 -08:00
  • 1978f59ffd chore: update workflow templates to v0.8.42 (#12491) ComfyUI Wiki 2026-02-17 06:33:43 +08:00
  • 88e6370527 Remove workaround for old pytorch. (#12480) comfyanonymous 2026-02-15 17:43:53 -08:00
  • c0370044cd MPDynamic: force load flux img_in weight (Fixes flux1 canny+depth lora crash) (#12446) rattus 2026-02-15 17:30:09 -08:00
  • ecd2a19661 Fix lora Extraction in offload conditions (+ dynamic_vram mode) (#12479) rattus 2026-02-15 17:28:51 -08:00
  • 2c1d06a4e3 feat(api-nodes): add Bria RMBG nodes (#12465) Alexander Piskun 2026-02-16 03:22:30 +02:00
  • e2c71ceb00 feat(api-nodes-Tencent): add ModelTo3DUV, 3DTextureEdit, 3DParts nodes (#12428) Alexander Piskun 2026-02-15 15:33:18 +02:00
  • 596ed68691 Node Replacement API (#12014) Jedrzej Kosinski 2026-02-15 02:12:30 -08:00
  • ce4a1ab48d chore(api-nodes): remove "gpt-4o" model (#12467) Alexander Piskun 2026-02-15 11:31:59 +02:00
  • e1ede29d82 Remove unsafe pickle loading code that was used on pytorch older than 2.4 (#12473) comfyanonymous 2026-02-14 19:53:52 -08:00
  • df1e5e8514 Update frontend package to 1.38.14 (#12469) Christian Byrne 2026-02-14 11:01:10 -08:00
  • dc9822b7df Add working Qwen 2512 ControlNet (Fun ControlNet) support (#12359) krigeta 2026-02-14 08:53:52 +05:30
  • 712efb466b Add left padding to LTXAV text encoder. (#12456) comfyanonymous 2026-02-13 18:56:54 -08:00
  • 726af73867 Fix some custom nodes. (#12455) comfyanonymous 2026-02-13 17:21:10 -08:00
  • 831351a29e Support generating attention masks for left padded text encoders. (#12454) comfyanonymous 2026-02-13 17:15:23 -08:00
  • e1add563f9 Use torch RMSNorm for flux models and refactor hunyuan video code. (#12432) comfyanonymous 2026-02-13 12:35:13 -08:00
  • 8902907d7a dynamic_vram: Training fixes (#12442) rattus 2026-02-13 12:29:37 -08:00