Commit Graph

  • 2d3fa73b02 Update submodule reference main wuyingwen 2025-06-08 17:50:48 +08:00
  • b1ea3aba41 Initial commit wuyingwen 2025-06-08 17:44:58 +08:00
  • c7c025b8d1
    Adjust memory estimation code for ACE VAE. (#7990) comfyanonymous 2025-05-07 22:22:23 -07:00
  • fd08e39588
    Make torchaudio not a hard requirement. (#7987) comfyanonymous 2025-05-07 18:37:12 -07:00
  • 56b6ee6754
    Detection code to make ltxv models without config work. (#7986) comfyanonymous 2025-05-07 18:28:24 -07:00
  • cc33cd3422
    Experimental lyrics strength for ACE. (#7984) comfyanonymous 2025-05-07 16:22:07 -07:00
  • b9980592c4
    Refuse to load api nodes on old pyav version. (#7981) comfyanonymous 2025-05-07 14:27:16 -07:00
  • 16417b40d9
    Initial ACE-Step model implementation. (#7972) comfyanonymous 2025-05-07 05:33:34 -07:00
  • 271c9c5b9e
    Better mem estimation for the LTXV 13B model. (#7963) comfyanonymous 2025-05-06 06:52:37 -07:00
  • a4e679765e
    Change chroma to use Flux shift. (#7961) comfyanonymous 2025-05-06 06:00:01 -07:00
  • 0cf2e46b17 ComfyUI version 0.3.32 comfyanonymous 2025-05-06 07:39:54 -04:00
  • 094e9ef126
    Add a way to disable api nodes: --disable-api-nodes (#7960) comfyanonymous 2025-05-06 01:53:53 -07:00
  • 1271c4ef9d
    More API Nodes (#7956) Jedrzej Kosinski 2025-05-06 03:23:00 -05:00
  • d9c80a85e5
    This should not be a warning. (#7946) comfyanonymous 2025-05-05 04:49:07 -07:00
  • 3e62c5513a
    make audio chunks contiguous before encoding (#7942) Christian Byrne 2025-05-04 20:27:23 -07:00
  • cd18582578
    Support saving Comfy VIDEO type to buffer (#7939) Christian Byrne 2025-05-04 20:26:57 -07:00
  • 80a44b97f5
    Change lumina to native RMSNorm. (#7935) comfyanonymous 2025-05-04 03:39:23 -07:00
  • 9187a09483
    Change cosmos and hydit models to use the native RMSNorm. (#7934) comfyanonymous 2025-05-04 03:26:20 -07:00
  • 3041e5c354
    Switch mochi and wan modes to use pytorch RMSNorm. (#7925) comfyanonymous 2025-05-03 16:07:55 -07:00
  • 7689917113 ComfyUI version 0.3.31 comfyanonymous 2025-05-03 00:34:01 -04:00
  • 486ad8fdc5
    Fix updater issue with newer portable. (#7917) comfyanonymous 2025-05-02 21:28:10 -07:00
  • 065d855f14
    upstream Preview Any from rgthree-comfy (#7815) Terry Jia 2025-05-02 13:15:54 -04:00
  • 530494588d
    [BugFix] Update frontend 1.18.6 (#7910) Chenlei Hu 2025-05-02 13:14:52 -04:00
  • 2ab9618732
    Fix the bugs in OFT/BOFT moule (#7909) Kohaku-Blueleaf 2025-05-03 01:12:37 +08:00
  • d9a87c1e6a
    Fix outdated comment about Internet connectivity (#7827) catboxanon 2025-05-02 05:28:27 -04:00
  • 551fe8dcee
    Add node to extend sigmas (#7901) catboxanon 2025-05-02 05:28:05 -04:00
  • ff99861650
    Make clipsave work with more TE models. (#7908) comfyanonymous 2025-05-02 02:15:32 -07:00
  • 8d0661d0ba
    Lint instance methods (#7903) catboxanon 2025-05-01 19:32:04 -04:00
  • 6d32dc049e
    Update frontend to v1.18 (#7898) Chenlei Hu 2025-05-01 10:57:54 -04:00
  • aa9d759df3
    Switch ltxv to use the pytorch RMSNorm. (#7897) comfyanonymous 2025-05-01 03:33:42 -07:00
  • c6c19e9980
    fix bug (#7894) Christian Byrne 2025-05-01 00:24:32 -07:00
  • 08ff5fa08a Cleanup chroma PR. comfyanonymous 2025-04-30 20:57:30 -04:00
  • 4ca3d84277
    Support for Chroma - Flux1 Schnell distilled with CFG (#7355) Silver 2025-05-01 02:57:00 +02:00
  • 39c27a3705
    Add updater test to stable release workflow. (#7887) comfyanonymous 2025-04-30 11:42:18 -07:00
  • b1c7291569
    Test updater in the windows release workflow. (#7886) comfyanonymous 2025-04-30 11:18:20 -07:00
  • dbc726f80c
    Better vace memory estimation. (#7875) comfyanonymous 2025-04-29 17:42:00 -07:00
  • 7ee96455e2
    Bump minimum pyav version to 14.2.0 (#7874) comfyanonymous 2025-04-29 17:38:45 -07:00
  • 0a66d4b0af
    Per device stream counters for async offload. (#7873) comfyanonymous 2025-04-29 17:28:52 -07:00
  • 5c5457a4ef
    support more example folders (#7836) Terry Jia 2025-04-29 11:28:04 -04:00
  • 45503f6499
    Add release process section to README (#7855) Chenlei Hu 2025-04-29 06:32:34 -04:00
  • 005a91ce2b
    Latest desktop and portable should work on blackwell. (#7861) comfyanonymous 2025-04-29 03:29:38 -07:00
  • 68f0d35296
    Add support for VIDEO as a built-in type (#7844) guill 2025-04-29 02:58:00 -07:00
  • 83d04717b6
    Support HiDream E1 model. (#7857) comfyanonymous 2025-04-28 12:01:15 -07:00
  • 7d329771f9
    Add moderation level option to OpenAIGPTImage1 node and update api_call method signature (#7804) Yoland Yan 2025-04-28 10:59:22 -07:00
  • c15909bb62
    CFG++ for gradient estimation sampler (#7809) chaObserv 2025-04-29 01:51:35 +08:00
  • 772b4c5945
    ltxv: overwrite existing mask on conditioned frame. (#7845) Andrew Kvochko 2025-04-28 20:42:04 +03:00
  • 5a50c3c7e5
    Fix stream priority to support older pytorch. (#7856) comfyanonymous 2025-04-28 10:07:21 -07:00
  • 30159a7fe6
    Save v pred zsnr metadata (#7840) Pam 2025-04-28 22:03:21 +05:00
  • cb9ac3db58
    ltxv: add strength parameter to conditioning. (#7849) Andrew Kvochko 2025-04-28 19:59:17 +03:00
  • 8115a7895b
    Add /api/v2/userdata endpoint (#7817) Benjamin Lu 2025-04-27 20:06:55 -04:00
  • c8cd7ad795
    Use stream for casting if enabled. (#7833) comfyanonymous 2025-04-27 02:38:11 -07:00
  • 542b4b36b6
    Prevent custom nodes from hooking certain functions. (#7825) comfyanonymous 2025-04-26 17:52:56 -07:00
  • ac10a0d69e
    Make loras work with --async-offload (#7824) comfyanonymous 2025-04-26 16:56:22 -07:00
  • 0dcc75ca54
    Add experimental --async-offload lowvram weight offloading. (#7820) comfyanonymous 2025-04-26 13:11:21 -07:00
  • b685b8a4e0
    Update portable package workflow to cu128 (#7812) comfyanonymous 2025-04-26 01:43:12 -07:00
  • 23e39f2ba7
    Add a T5TokenizerOptions node to set options for the T5 tokenizer. (#7803) comfyanonymous 2025-04-25 16:36:00 -07:00
  • 78992c4b25
    [NodeDef] Add documentation on widgetType (#7768) AustinMroz 2025-04-25 12:35:07 -05:00
  • f935d42d8e Support SimpleTuner lycoris lora format for HiDream. comfyanonymous 2025-04-25 03:11:14 -04:00
  • a97f2f850a ComfyUI version 0.3.30 comfyanonymous 2025-04-24 16:03:01 -04:00
  • 5acb705857
    Switch LTXVPreprocess to libx264 (#7776) comfyanonymous 2025-04-24 10:58:31 -07:00
  • 5c80da31db
    fix multiple image return from api nodes (#7772) thot experiment 2025-04-24 00:29:05 -07:00
  • e2eed9eb9b
    throw away alpha channel in clip vision preprocessor (#7769) thot experiment 2025-04-23 18:28:36 -07:00
  • 11b68ebd22
    [BugFix] Update frontend to 1.17.11 (#7766) filtered 2025-04-24 08:16:12 +10:00
  • 188b383c35
    change timeout to 7 days (#7765) thot experiment 2025-04-23 14:53:34 -07:00
  • 2c1d686ec6
    implement multi image prompting for gpt-image-1 and fix transparency in outputs (#7763) thot experiment 2025-04-23 13:10:10 -07:00
  • e8ddc2be95
    [BugFix] Update frontend to 1.17.10 (#7762) filtered 2025-04-24 06:02:41 +10:00
  • dea1c7474a
    Add support for API Nodes in ComfyUI. (#7726) Robin Huang 2025-04-23 12:38:34 -07:00
  • 154f2911aa
    Lower size of release package more. (#7754) comfyanonymous 2025-04-23 03:33:09 -07:00
  • 3eaad0590e
    Lower size of release package. (#7751) comfyanonymous 2025-04-23 02:47:09 -07:00
  • 7eaff81be1
    fp16 accumulation can now be enabled on the stable package. (#7750) comfyanonymous 2025-04-23 02:28:24 -07:00
  • 21a11ef817
    Pytorch stable 2.7 is out and support cu128 (#7749) comfyanonymous 2025-04-23 02:12:59 -07:00
  • 552615235d
    Fix for dino lowvram. (#7748) comfyanonymous 2025-04-23 01:12:52 -07:00
  • 0738e4ea5d
    [API nodes] Add backbone for supporting api nodes in ComfyUI (#7745) Robin Huang 2025-04-22 23:18:08 -07:00
  • 92cdc692f4
    Replace aom-av1 with svt-av1 for saving webm videos, use preset 6 + yuv420p10le pixel format (#7736) Alex Butler 2025-04-22 22:57:17 +01:00
  • 2d6805ce57
    Add option for using fp8_e8m0fnu for model weights. (#7733) comfyanonymous 2025-04-22 03:17:38 -07:00
  • a8f63c0d5b
    Support dora_scale on both axis (#7727) Kohaku-Blueleaf 2025-04-22 17:01:27 +08:00
  • 454a635c1b
    upstream MaskPreview from ComfyUI_essentials (#7719) Terry Jia 2025-04-22 05:00:28 -04:00
  • 966c43ce26
    Add OFT/BOFT algorithm in weight adapter (#7725) Kohaku-Blueleaf 2025-04-22 16:59:47 +08:00
  • 3ab231f01f
    Fix issue with WAN VACE implementation. (#7724) comfyanonymous 2025-04-21 20:36:12 -07:00
  • 1f3fba2af5
    Unified Weight Adapter system for better maintainability and future feature of Lora system (#7540) Kohaku-Blueleaf 2025-04-22 08:15:32 +08:00
  • 5d0d4ee98a
    Add strength control for vace. (#7717) comfyanonymous 2025-04-21 16:36:20 -07:00
  • 9d57b8afd8
    Update nodes_primitive.py (#7716) Alexander G. Morano 2025-04-21 18:51:31 -04:00
  • 5d51794607
    Add node type hint for socketless option (#7714) filtered 2025-04-22 06:13:00 +10:00
  • ce22f687cc
    Support for WAN VACE preview model. (#7711) comfyanonymous 2025-04-21 11:40:29 -07:00
  • b6fd3ffd10
    Populate AUTH_TOKEN_COMFY_ORG hidden input (#7709) Chenlei Hu 2025-04-21 14:39:45 -04:00
  • 11b72c9c55
    CLIPTextEncodeHiDream. (#7703) comfyanonymous 2025-04-20 23:41:51 -07:00
  • 2c735c13b4
    Slightly better fix for #7687 comfyanonymous 2025-04-20 08:33:27 -07:00
  • fd27494441 Use empty t5 of size 128 for hidream, seems to give closer results. comfyanonymous 2025-04-19 19:49:40 -04:00
  • f43e1d7f41
    Hidream: Allow loading hidream text encoders in CLIPLoader and DualCLIPLoader (#7676) power88 2025-04-20 07:47:30 +08:00
  • 4486b0d0ff
    Update CODEOWNERS and add christian-byrne (#7663) Yoland Yan 2025-04-19 14:23:31 -07:00
  • 636d4bfb89 Fix hard crash when the spiece tokenizer path is bad. comfyanonymous 2025-04-19 15:55:43 -04:00
  • dc300a4569
    Add wanfun template workflows. (#7678) Robin Huang 2025-04-19 12:21:46 -07:00
  • f3b09b9f2d
    [BugFix] Update frontend to 1.16.9 (#7655) Chenlei Hu 2025-04-18 15:12:42 -04:00
  • 7ecd5e9614 Increase freq_cutoff in FreSca node. comfyanonymous 2025-04-18 03:16:16 -04:00
  • 2383a39e3b
    Replace CLIPType if with getattr (#7589) City 2025-04-18 08:53:36 +02:00
  • 34e06bf7ec
    add support to output camera state (#7582) Terry Jia 2025-04-18 02:52:18 -04:00
  • 55822faa05
    [Type] Annotate graph.get_input_info (#7386) Chenlei Hu 2025-04-17 21:02:24 -04:00
  • 880c205df1 Add hidream to readme. comfyanonymous 2025-04-17 16:58:27 -04:00
  • 3dc240d089 Make fresca work on multi dim. comfyanonymous 2025-04-17 15:46:41 -04:00
  • 19373aee75
    Add FreSca node (#7631) BVH 2025-04-18 00:54:33 +05:30