Commit Graph

  • 661e1043d1 qwen image vae decode memory_used_decode update from 2050 to 2200 jiangchengchengark 2025-12-09 14:34:47 +08:00
  • 9d252f3b70
    ops: delete dead code (#11204) rattus 2025-12-09 15:55:13 +10:00
  • 2261bad06d ops: delete dead code Rattus 2025-12-09 15:39:34 +10:00
  • 8c63b6d412 Delete the qwen-image vae check branch and use shape[2] to perform memory calculation jiangchengchengark 2025-12-09 13:10:16 +08:00
  • 840b624c32
    bump comfyui-frontend-package to 1.34.7 christian-byrne-patch-2 Christian Byrne 2025-12-08 21:59:01 -07:00
  • b9fb542703
    add chroma-radiance-x0 mode (#11197) Lodestone 2025-12-09 11:33:29 +07:00
  • 334e74b938
    Merge branch 'master' into portable-manager-update Jedrzej Kosinski 2025-12-08 20:25:28 -08:00
  • 34ecc0e0fc ruff linter lodestone-rock 2025-12-09 11:22:34 +07:00
  • cabc4d351f
    bump comfyui-frontend-package to 1.33.13 (patch) (#11200) Christian Byrne 2025-12-08 20:22:02 -08:00
  • e136b6dbb0
    dequantization offload accounting (fixes Flux2 OOMs - incl TEs) (#11171) rattus 2025-12-09 14:21:31 +10:00
  • d50f342c90
    Fix potential issue. (#11201) comfyanonymous 2025-12-08 20:20:04 -08:00
  • 4304fdb89c
    Fix potential issue. comfyanonymous 2025-12-08 23:17:55 -05:00
  • cdb054d2ec
    bump comfyui-frontend-package to 1.33.13 (patch) Christian Byrne 2025-12-08 20:54:33 -07:00
  • a22b6cfbe6 delete debug print lodestone-rock 2025-12-09 10:52:25 +07:00
  • 3711e9462f delete debug print lodestone-rock 2025-12-09 10:50:39 +07:00
  • 8ec0e3e6e3 tensor Haoming 2025-12-09 11:46:20 +08:00
  • 846a019fc2 tensor Haoming 2025-12-09 11:44:12 +08:00
  • 01fa7b03c3 Create a new branch for GPU memory calculations in qwen-image vae jiangchengchengark 2025-12-09 11:33:50 +08:00
  • 9e006c3fa3 add chroma-radiance-x0 mode lodestone-rock 2025-12-09 09:02:02 +07:00
  • 9663183774 Set the compute type on CLIP MPs Rattus 2025-12-07 21:25:47 +10:00
  • 5a7e929849 Account for dequantization and type-casts in offload costs Rattus 2025-12-07 21:23:05 +10:00
  • 482a9d58a8 make setattr safe for non existent attributes Rattus 2025-12-07 20:53:01 +10:00
  • 460b848669 address comments Richard Yu 2025-12-08 14:54:53 -08:00
  • 3b0368aa34
    Fix regression. (#11194) comfyanonymous 2025-12-08 14:38:36 -08:00
  • 6e520d6d96
    Fix regression. comfyanonymous 2025-12-08 17:38:09 -05:00
  • 5c781dfd98 Handle the None case for the dtype Rattus 2025-12-09 08:32:14 +10:00
  • f030b3afc8 mostly fixing mistakes Yousef Rafat 2025-12-09 00:16:17 +02:00
  • 86590ca403 fix non dict nodes Richard Yu 2025-12-08 13:32:23 -08:00
  • 935493f6c1
    chore: update workflow templates to v0.7.54 (#11192) ComfyUI Wiki 2025-12-09 04:18:53 +08:00
  • 60ee574748
    retune lowVramPatch VRAM accounting (#11173) rattus 2025-12-09 06:18:06 +10:00
  • 8e889c535d
    Support "transformer." LoRA prefix for Z-Image (#11135) dxqb 2025-12-08 21:17:26 +01:00
  • 89ed96021e chore: update workflow templates to v0.7.54 ComfyUI Wiki 2025-12-09 03:45:55 +08:00
  • 0727f6978b Fix: filter hidden files from /internal/files endpoint Johnpaul 2025-12-08 19:31:09 +01:00
  • c764864ab0
    Merge branch 'master' into my-fix Vijaysinh 2025-12-08 19:57:11 +05:30
  • 460e9e0d8a Added new feature/fix for ComfyUI Vijay2359 2025-12-08 19:32:25 +05:30
  • 9e10cbe5d6
    Merge branch 'comfyanonymous:master' into master patientx 2025-12-08 15:10:45 +03:00
  • e3131abac6
    Disable flash attention in zluda.py patientx 2025-12-08 15:10:12 +03:00
  • a8ea6953ec Fix Z Image FP16 overflow via downscaling vanDuven 2025-12-08 05:43:00 -05:00
  • fd271dedfd
    [API Nodes] add support for seedance-1-0-pro-fast model (#10947) Alexander Piskun 2025-12-08 11:33:46 +02:00
  • c3c6313fc7
    Added "system_prompt" input to Gemini nodes (#11177) Alexander Piskun 2025-12-08 11:28:17 +02:00
  • 85c4b4ae26
    chore: replace imports of deprecated V1 classes (#11127) Alexander Piskun 2025-12-08 11:27:02 +02:00
  • 058f084371
    Update workflow templates to v0.7.51 (#11150) ComfyUI Wiki 2025-12-08 17:22:51 +08:00
  • ec7f65187d
    chore(comfy_api): replace absolute imports with relative (#11145) Alexander Piskun 2025-12-08 11:21:41 +02:00
  • 211fa31880
    Merge branch 'master' into refine_offload Yao Chi 2025-12-08 15:54:11 +08:00
  • fb8bdb7590
    Fix duplicate model_management initialization in hunyuan_video upsampler.py Apophis3158 2025-12-08 07:09:44 +08:00
  • 44a5bf353a testing the model Yousef Rafat 2025-12-07 23:43:49 +02:00
  • 389515d350
    Merge branch 'comfyanonymous:master' into master patientx 2025-12-07 23:03:15 +03:00
  • 4b9332cc21 continue building nodes / testing vae Yousef Rafat 2025-12-07 21:41:14 +02:00
  • 7cecb6dbf8 worker/executor with subprocess executor khimaros 2025-12-05 18:21:55 -08:00
  • 277e46473d
    Merge branch 'comfyanonymous:master' into master Extraltodeus 2025-12-07 17:24:23 +01:00
  • c6eb7f7cf1
    Added "system_prompt" input to Gemini nodes bigcat88 2025-12-07 17:27:38 +02:00
  • f43ff9fcbd retune lowVramPatch VRAM accounting Rattus 2025-12-07 22:47:18 +10:00
  • 56fa7dbe38
    Properly load the newbie diffusion model. (#11172) comfyanonymous 2025-12-07 04:44:55 -08:00
  • 156605802b Properly load the newbie diffusion model. comfyanonymous 2025-12-07 07:39:26 -05:00
  • d3d75415ff
    Merge branch 'comfyanonymous:master' into feature/custom-node-paths-cli-args Sas van Gulik 2025-12-07 12:31:55 +01:00
  • 6420b47885
    Merge branch 'comfyanonymous:master' into master patientx 2025-12-07 14:10:24 +03:00
  • 7ec1656735
    Merge branch 'comfyanonymous:master' into offloader-maifee Maifee Ul Asad 2025-12-07 15:32:22 +06:00
  • 2043ca2b61 Clear filename list cache to allow rebuilding the list when the "/object_info" endpoint is called Udhul 2025-12-07 07:35:16 +01:00
  • aa2ab2415c Docs: Add Chinese README translation 不成眠 2025-12-07 11:46:35 +08:00
  • 329480da5a
    Fix qwen scaled fp8 not working with kandinsky. Make basic t2i wf work. (#11162) comfyanonymous 2025-12-06 17:50:10 -08:00
  • 4d53b484f3 Fix qwen scaled fp8 not working with kandinsky. Make basic t2i wf work. comfyanonymous 2025-12-06 20:36:08 -05:00
  • 4086acf3c2
    Fix on-load VRAM OOM (#11144) rattus 2025-12-07 09:42:09 +10:00
  • 50ca97e776
    Speed up lora compute and lower memory usage by doing it in fp16. (#11161) comfyanonymous 2025-12-06 15:36:20 -08:00
  • dc09377bd8 Speed up lora compute and lower memory usage by doing it in fp16. comfyanonymous 2025-12-06 18:29:51 -05:00
  • 041dbd6a8a add nodes Yousef Rafat 2025-12-07 01:00:08 +02:00
  • 31273434f1
    Merge branch 'comfyanonymous:master' into master patientx 2025-12-07 01:41:57 +03:00
  • 08d93555d0 init Yousef Rafat 2025-12-06 23:18:10 +02:00
  • ebb466d4f8 Merge branch 'v3-improvements' of https://github.com/comfyanonymous/ComfyUI into v3-improvements Jedrzej Kosinski 2025-12-06 13:14:24 -08:00
  • e2bc6301af Merge branch 'master' into v3-improvements Jedrzej Kosinski 2025-12-06 13:14:20 -08:00
  • 7ac7d69d94
    Fix EmptyAudio node input types (#11149) Jukka Seppänen 2025-12-06 20:09:44 +02:00
  • 6065a92b94
    Update template to 0.7.51 ComfyUI Wiki 2025-12-07 00:48:19 +08:00
  • 863551214b chore: update workflow templates to v0.7.50 ComfyUI Wiki 2025-12-07 00:16:31 +08:00
  • 1196934ab7 Fix EmptyAudio node input types kijai 2025-12-06 17:05:58 +02:00
  • 1e4f506f03 Initial HYV1.5 manual FLF implementation kabachuha 2025-12-06 17:25:47 +03:00
  • 323679968e
    Merge branch 'comfyanonymous:master' into master patientx 2025-12-06 17:15:18 +03:00
  • 970c107ff8 add account for reserved VRAM gap by CudaMallocAsync on extra memory Balladie 2025-12-06 12:25:11 +00:00
  • 76f18e955d
    marked all Pika API nodes a deprecated (#11146) Alexander Piskun 2025-12-06 13:28:08 +02:00
  • c4ea432a0a
    marked all Pika API nodes a deprecated bigcat88 2025-12-06 11:27:12 +02:00
  • d5f7e8d8c3
    chore(comfy_api): replace absolute imports with relative bigcat88 2025-12-05 11:52:38 +02:00
  • deff0ac835 Fix on-load VRAM OOM Rattus 2025-12-06 17:14:30 +10:00
  • 00984ec4b0
    chore: replace imports of deprecated V1 classes bigcat88 2025-12-05 11:50:48 +02:00
  • d7a0aef650
    Set OCL_SET_SVM_SIZE on AMD. (#11139) comfyanonymous 2025-12-05 21:15:21 -08:00
  • a28293eba7 Set OCL_SET_SVM_SIZE on AMD. comfyanonymous 2025-12-06 00:10:49 -05:00
  • 0b78859e09 Make MatchType's output default displayname "MATCHTYPE" Jedrzej Kosinski 2025-12-05 20:39:25 -08:00
  • a2a22cee9d Merge branch 'v3-improvements' of https://github.com/comfyanonymous/ComfyUI into v3-improvements Jedrzej Kosinski 2025-12-05 20:28:31 -08:00
  • ffdfcafa7b Merge branch 'master' into v3-improvements Jedrzej Kosinski 2025-12-05 20:28:28 -08:00
  • 913f86b727
    [V3] convert nodes_mask.py to V3 schema (#10669) Alexander Piskun 2025-12-06 06:24:10 +02:00
  • 117bf3f2bd
    convert nodes_freelunch.py to the V3 schema (#10904) Alexander Piskun 2025-12-06 06:22:02 +02:00
  • ae676ed105
    Fix regression. (#11137) comfyanonymous 2025-12-05 20:01:19 -08:00
  • cdb2597000
    Fix regression. comfyanonymous 2025-12-05 23:00:58 -05:00
  • fd109325db
    Kandinsky5 model support (#10988) Jukka Seppänen 2025-12-06 05:20:22 +02:00
  • 96fb67be5f
    Merge 5c6fcbda91babbefc6d907a7febe3c0450f05f74 into bed12674a1d2c4bfdfbdd098686390f807996c90 Haoming 2025-12-06 07:59:18 +07:00
  • 1d74168209
    Update README.md patientx 2025-12-06 03:58:41 +03:00
  • 81e364f3db
    Merge branch 'comfyanonymous:master' into master patientx 2025-12-06 03:58:11 +03:00
  • 6e5da08585
    Update README.md patientx 2025-12-06 03:58:04 +03:00
  • 51119d3283
    Support "transformer." LoRA prefix for Z-Image dxqb 2025-12-06 01:28:18 +01:00
  • f28e0c257c Fix NormalizeVideoLatentStart node out on non-op kijai 2025-12-06 02:15:47 +02:00
  • bed12674a1
    docs: add ComfyUI-Manager documentation and update to v4.0.3b4 (#11133) Dr.Lt.Data 2025-12-06 08:45:38 +09:00
  • 092ee8a500
    Fix some custom nodes. (#11134) comfyanonymous 2025-12-05 15:25:31 -08:00
  • 46d22a3c72 Fix some custom nodes. comfyanonymous 2025-12-05 18:20:38 -05:00