Commit Graph

Select branches

Hide Pull Requests

master

Mono Color

• 93948e3fc5 feat(api-nodes): enable Kling Omni O1 node (#11229) Alexander PiskunandGitHub 2025-12-11 08:11:12 +02:00
• e711aaf1a7 Lower VAE loading requirements：Create a new branch for GPU memory calculations in qwen-image vae (#11199) FarshoreandGitHub 2025-12-11 11:02:26 +08:00
• 57ddb7fd13 Fix: filter hidden files from /internal/files endpoint (#11191) Johnpaul ChiweteluandGitHub 2025-12-11 03:49:49 +01:00
• 17c92a9f28 Tweak Z Image memory estimation. (#11254) comfyanonymousandGitHub 2025-12-10 16:59:48 -08:00
• 36357bbcc3 process the NodeV1 dict results correctly (#11237) Alexander PiskunandGitHub 2025-12-10 21:55:09 +02:00
• f668c2e3c9 bump comfyui-frontend-package to 1.34.8 (#11220) Benjamin LuandGitHub 2025-12-09 19:27:07 -08:00
• fc657f471a ComfyUI version v0.4.0 comfyanonymous 2025-12-09 18:22:09 -05:00
• 791e30ff50 Fix nan issue when quantizing fp16 tensor. (#11213) comfyanonymousandGitHub 2025-12-09 14:03:21 -08:00
• e2a800e7ef Fix for HunyuanVideo1.5 meanflow distil (#11212) Jukka SeppänenandGitHub 2025-12-09 23:59:16 +02:00
• 9d252f3b70 ops: delete dead code (#11204) rattusandGitHub 2025-12-09 15:55:13 +10:00
• b9fb542703 add chroma-radiance-x0 mode (#11197) LodestoneandGitHub 2025-12-09 11:33:29 +07:00
• cabc4d351f bump comfyui-frontend-package to 1.33.13 (patch) (#11200) Christian ByrneandGitHub 2025-12-08 20:22:02 -08:00
• e136b6dbb0 dequantization offload accounting (fixes Flux2 OOMs - incl TEs) (#11171) rattusandGitHub 2025-12-09 14:21:31 +10:00
• d50f342c90 Fix potential issue. (#11201) comfyanonymousandGitHub 2025-12-08 20:20:04 -08:00
• 3b0368aa34 Fix regression. (#11194) comfyanonymousandGitHub 2025-12-08 14:38:36 -08:00
• 935493f6c1 chore: update workflow templates to v0.7.54 (#11192) ComfyUI WikiandGitHub 2025-12-09 04:18:53 +08:00
• 60ee574748 retune lowVramPatch VRAM accounting (#11173) rattusandGitHub 2025-12-09 06:18:06 +10:00
• 8e889c535d Support "transformer." LoRA prefix for Z-Image (#11135) dxqbandGitHub 2025-12-08 21:17:26 +01:00
• fd271dedfd [API Nodes] add support for seedance-1-0-pro-fast model (#10947) Alexander PiskunandGitHub 2025-12-08 11:33:46 +02:00
• c3c6313fc7 Added "system_prompt" input to Gemini nodes (#11177) Alexander PiskunandGitHub 2025-12-08 11:28:17 +02:00
• 85c4b4ae26 chore: replace imports of deprecated V1 classes (#11127) Alexander PiskunandGitHub 2025-12-08 11:27:02 +02:00
• 058f084371 Update workflow templates to v0.7.51 (#11150) ComfyUI WikiandGitHub 2025-12-08 17:22:51 +08:00
• ec7f65187d chore(comfy_api): replace absolute imports with relative (#11145) Alexander PiskunandGitHub 2025-12-08 11:21:41 +02:00
• 56fa7dbe38 Properly load the newbie diffusion model. (#11172) comfyanonymousandGitHub 2025-12-07 04:44:55 -08:00
• 329480da5a Fix qwen scaled fp8 not working with kandinsky. Make basic t2i wf work. (#11162) comfyanonymousandGitHub 2025-12-06 17:50:10 -08:00
• 4086acf3c2 Fix on-load VRAM OOM (#11144) rattusandGitHub 2025-12-07 09:42:09 +10:00
• 50ca97e776 Speed up lora compute and lower memory usage by doing it in fp16. (#11161) comfyanonymousandGitHub 2025-12-06 15:36:20 -08:00
• 7ac7d69d94 Fix EmptyAudio node input types (#11149) Jukka SeppänenandGitHub 2025-12-06 20:09:44 +02:00
• 76f18e955d marked all Pika API nodes a deprecated (#11146) Alexander PiskunandGitHub 2025-12-06 13:28:08 +02:00
• d7a0aef650 Set OCL_SET_SVM_SIZE on AMD. (#11139) comfyanonymousandGitHub 2025-12-05 21:15:21 -08:00
• 913f86b727 [V3] convert nodes_mask.py to V3 schema (#10669) Alexander PiskunandGitHub 2025-12-06 06:24:10 +02:00
• 117bf3f2bd convert nodes_freelunch.py to the V3 schema (#10904) Alexander PiskunandGitHub 2025-12-06 06:22:02 +02:00
• ae676ed105 Fix regression. (#11137) comfyanonymousandGitHub 2025-12-05 20:01:19 -08:00
• fd109325db Kandinsky5 model support (#10988) Jukka SeppänenandGitHub 2025-12-06 05:20:22 +02:00
• bed12674a1 docs: add ComfyUI-Manager documentation and update to v4.0.3b4 (#11133) Dr.Lt.DataandGitHub 2025-12-06 08:45:38 +09:00
• 092ee8a500 Fix some custom nodes. (#11134) comfyanonymousandGitHub 2025-12-05 15:25:31 -08:00
• 79d17ba233 Context windows fixes and features (#10975) 4 people 2025-12-05 22:42:46 +02:00
• 6fd463aec9 Fix regression when text encoder loaded directly on GPU. (#11129) comfyanonymousandGitHub 2025-12-05 12:33:16 -08:00
• 43071e3de3 Make old scaled fp8 format use the new mixed quant ops system. (#11000) comfyanonymousandGitHub 2025-12-05 11:35:42 -08:00
• 0ec05b1481 Remove line made unnecessary (and wrong) after transformer_options was added to NextDiT's _forward definition (#11118) Jedrzej KosinskiandGitHub 2025-12-05 11:05:38 -08:00
• f00b249708 Documentation for socket activation andreas 2025-12-05 18:11:27 +01:00
• 35fa091340 Forgot to put this in README. (#11112) comfyanonymousandGitHub 2025-12-04 19:52:09 -08:00
• 3c8456223c [API Nodes]: fixes and refactor (#11104) Alexander PiskunandGitHub 2025-12-05 00:05:28 +02:00
• 9bc893c5bb sd: bump HY1.5 VAE estimate (#11107) rattusandGitHub 2025-12-05 03:50:36 +10:00
• f4bdf5f830 sd: revise hy VAE VRAM (#11105) rattusandGitHub 2025-12-05 03:50:04 +10:00
• 6be85c7920 mp: use look-ahead actuals for stream offload VRAM calculation (#11096) rattusandGitHub 2025-12-04 14:28:44 +10:00
• ea17add3c6 Fix case where text encoders where running on the CPU instead of GPU. (#11095) comfyanonymousandGitHub 2025-12-03 20:15:15 -08:00
• ecdc8697d5 Qwen Image Lora training fix from #11090 (#11094) comfyanonymousandGitHub 2025-12-03 19:49:28 -08:00
• dce518c2b4 convert nodes_audio.py to V3 schema (#10798) Alexander PiskunandGitHub 2025-12-04 03:35:04 +02:00
• 03be08f325 Socket activation working andreas 2025-12-03 23:18:35 +01:00
• 943105ccef Allow reuse of socket (works without SELinux, probably no longer needed with proper workaround) andreas 2025-12-03 23:00:05 +01:00
• 440268d394 convert nodes_load_3d.py to V3 schema (#10990) Alexander PiskunandGitHub 2025-12-03 23:52:31 +02:00
• c9d4b636e6 2nd iteration fix socket activation andreas 2025-12-03 22:45:28 +01:00
• 94b1730c24 First iteration fix socket activation andreas 2025-12-03 22:37:16 +01:00
• a860d809d1 Added dockerfile for ROCM container build andreas 2025-12-03 22:29:52 +01:00
• 87c104bfc1 add support for "@image" reference format in Kling Omni API nodes (#11082) Alexander PiskunandGitHub 2025-12-03 18:55:44 +02:00
• 19f2192d69 fix(V3-Schema): use empty list defaults for Schema.inputs/outputs/hidden to avoid None issues (#11083) Alexander PiskunandGitHub 2025-12-03 18:37:35 +02:00
• 519c941165 Prs/lora reservations (reduce massive Lora reservations especially on Flux2) (#11069) rattusandGitHub 2025-12-03 17:28:45 +10:00
• 861817d22d Fix issue with portable updater. (#11070) comfyanonymousandGitHub 2025-12-02 21:47:51 -08:00
• c120eee5ba Add MatchType, DynamicCombo, and Autogrow support to V3 Schema (#10832) Jedrzej KosinskiandGitHub 2025-12-02 21:17:13 -08:00
• 73f5649196 Implement temporal rolling VAE (Major VRAM reductions in Hunyuan and Kandinsky) (#10995) rattusandGitHub 2025-12-03 13:49:29 +10:00
• 3f512f5659 Added PATCH method to CORS headers (#11066) Jim HeisingandGitHub 2025-12-02 19:29:27 -08:00
• b94d394a64 Support Z Image alibaba pai fun controlnets. (#11062) comfyanonymousandGitHub 2025-12-02 18:38:31 -08:00
• 277237ccc1 attention: use flag based OOM fallback (#11038) rattusandGitHub 2025-12-03 08:24:19 +10:00
• daaceac769 Hack to make zimage work in fp16. (#11057) comfyanonymousandGitHub 2025-12-02 14:11:58 -08:00
• 6918fd1efe Rework socket activation andreas 2025-12-02 22:36:25 +01:00
• a2f1dc2bc6 First attempt at socket activation andreas 2025-12-02 22:20:22 +01:00
• 33d6aec3b7 add check for the format arg type in VideoFromComponents.save_to function (#11046) Alexander PiskunandGitHub 2025-12-02 21:50:13 +02:00
• 44baa0b7f3 Fix CODEOWNERS formatting to have all on the same line, otherwise only last line applies (#11053) Jedrzej KosinskiandGitHub 2025-12-02 11:46:29 -08:00
• a17cf1c387 Add @guill as a code owner (#11031) Yoland YanandGitHub 2025-12-01 19:40:44 -08:00
• b4a20acc54 feat: Support ComfyUI-Manager for pip version (#7555) Dr.Lt.DataandGitHub 2025-12-02 12:32:52 +09:00
• c55dc857d5 bump comfyui-frontend-package to 1.33.10 (#11028) Christian ByrneandGitHub 2025-12-01 17:56:38 -08:00
• 878db3a727 Implement the Ovis image model. (#11030) comfyanonymousandGitHub 2025-12-01 17:56:17 -08:00
• 30c259cac8 ComfyUI version v0.3.76 comfyanonymous 2025-12-01 20:25:35 -05:00
• 1cb7e22a95 [API Nodes] add Kling O1 model support (#11025) Alexander PiskunandGitHub 2025-12-02 02:11:52 +02:00
• 2640acb31c Update qwen tokenizer to add qwen 3 tokens. (#11029) comfyanonymousandGitHub 2025-12-01 14:13:48 -08:00
• 7dbd5dfe91 bump comfyui-frontend-package to 1.32.10 (#11018) Christian ByrneandGitHub 2025-12-01 10:27:17 -08:00
• f8b981ae9a Next AMD portable will have pytorch with ROCm 7.1.1 (#11002) comfyanonymousandGitHub 2025-11-30 01:21:31 -08:00
• 4967f81778 update template to 0.7.25 (#10996) ComfyUI WikiandGitHub 2025-11-30 10:07:26 +08:00
• 0a6746898d Make the ScaleRope node work on Z Image and Lumina. (#10994) comfyanonymousandGitHub 2025-11-29 15:00:55 -08:00
• 5151cff293 Add some missing z image lora layers. (#10980) comfyanonymousandGitHub 2025-11-28 20:55:00 -08:00
• af96d9812d feat(security): add System User protection with __ prefix (#10966) Dr.Lt.DataandGitHub 2025-11-29 11:28:42 +09:00
• 52a32e2b32 Support some z image lora formats. (#10978) comfyanonymousandGitHub 2025-11-28 18:12:42 -08:00
• b907085709 Support video tiny VAEs (#10884) Jukka SeppänenandGitHub 2025-11-29 02:40:19 +02:00
• 065a2fbbec Update driver link in AMD portable README (#10974) comfyanonymousandGitHub 2025-11-28 16:37:39 -08:00
• 0ff0457892 mm: wrap the raw stream in context manager (#10958) rattusandGitHub 2025-11-29 07:38:12 +10:00
• 6484ac89dc fix QuantizedTensor.is_contiguous (#10956) (#10959) Urle SistianaandGitHub 2025-11-29 05:33:07 +08:00
• f55c98a89f Disable offload stream when torch compile. (#10961) comfyanonymousandGitHub 2025-11-28 13:16:46 -08:00
• ca7808f240 fix(user_manager): fix typo in move_userdata dest validation (#10967) Dr.Lt.DataandGitHub 2025-11-29 05:43:17 +09:00
• 52e778fff3 feat(Kling-API-Nodes): add v2-5-turbo model to FirstLastFrame node (#10938) Alexander PiskunandGitHub 2025-11-28 12:52:59 +02:00
• 9d8a817985 Enable async offloading by default on Nvidia. (#10953) comfyanonymousandGitHub 2025-11-27 14:46:12 -08:00
• b59750a86a Update template to 0.7.23 (#10949) ComfyUI WikiandGitHub 2025-11-28 06:12:56 +08:00
• 3f382a4f98 quant ops: Dequantize weight in-place (#10935) rattusandGitHub 2025-11-28 02:06:30 +10:00
• f17251bec6 Account for the VRAM cost of weight offloading (#10733) rattusandGitHub 2025-11-27 16:03:03 +10:00
• c38e7d6599 block info (#10841) HaomingandGitHub 2025-11-27 12:28:44 +08:00
• eaf68c9b5b Make lora training work on Z Image and remove some redundant nodes. (#10927) comfyanonymousandGitHub 2025-11-26 16:25:32 -08:00
• cc6a8dcd1a Dataset Processing Nodes and Improved LoRA Trainer Nodes with multi resolution supports. (#10708) Kohaku-BlueleafandGitHub 2025-11-27 08:18:08 +08:00
• a2d60aad0f convert nodes_customer_sampler.py to V3 schema (#10206) Alexander PiskunandGitHub 2025-11-27 00:55:31 +02:00
• d8433c63fd chore(api-nodes): remove chat widgets from OpenAI/Gemini nodes (#10861) Alexander PiskunandGitHub 2025-11-27 00:42:01 +02:00
• dd41b74549 Add Z Image to readme. (#10924) comfyanonymousandGitHub 2025-11-26 12:36:38 -08:00