Commit Graph

  • 3ea3bc8546 Fix wan issues when prompt length is long. comfyanonymous 2025-02-26 20:34:02 -0500
  • 2ec396301a
    Merge 219237379c into 8e69e2ddfd Kang 2025-02-26 19:57:08 -0500
  • 2e24386ec1
    Merge 28d5474d76 into 8e69e2ddfd Diogo Santiago 2025-02-27 05:51:31 +0600
  • 8e69e2ddfd Bump ComfyUI version to v0.3.17 v0.3.17 comfyanonymous 2025-02-26 17:59:10 -0500
  • 0270a0b41c Reduce artifacts on Wan by doing the patch embedding in fp32. comfyanonymous 2025-02-26 16:59:26 -0500
  • 26c7baf789 Bump ComfyUI version to v0.3.16 v0.3.16 comfyanonymous 2025-02-26 14:30:32 -0500
  • c37f15f98e Add fast preview support for Wan models. comfyanonymous 2025-02-26 08:56:23 -0500
  • 4bca7367f3 Don't try to use clip_fea on t2v model. comfyanonymous 2025-02-26 08:38:09 -0500
  • b6fefe686b Better wan memory estimation. comfyanonymous 2025-02-26 07:51:22 -0500
  • fa62287f1f More code reuse in wan. comfyanonymous 2025-02-26 05:22:29 -0500
  • 0844998db3 Slightly better wan i2v mask implementation. comfyanonymous 2025-02-26 03:49:50 -0500
  • 2dac065cd7 Support Cambricon MLU huzhan 2025-02-25 14:43:13 +0800
  • 4ced06b879 WIP support for Wan I2V model. comfyanonymous 2025-02-26 01:49:43 -0500
  • cb06e9669b Wan seems to work with fp16. comfyanonymous 2025-02-25 21:37:12 -0500
  • 0c32f82298 Fix missing frames in SaveWEBM node. comfyanonymous 2025-02-25 20:21:03 -0500
  • 189da3726d
    Update README.md (#6960) Yoland Yan 2025-02-25 17:17:18 -0800
  • 9a66bb972d Make wan work with all latent resolutions. comfyanonymous 2025-02-25 19:56:04 -0500
  • 073c8424cb Fix typos (embeded > embedded) Margen67 2025-02-25 16:26:27 -0800
  • c85f4208a8 Update GitHub Actions Margen67 2025-02-25 16:20:35 -0800
  • ea0f939df3 Fix issue with wan and other attention implementations. comfyanonymous 2025-02-25 19:13:39 -0500
  • f37551c1d2 Change wan rope implementation to the flux one. comfyanonymous 2025-02-25 19:11:14 -0500
  • 63023011b9 WIP support for Wan t2v model. comfyanonymous 2025-02-25 17:20:35 -0500
  • decce572f3 Fix attn_mask issue in DoubleStreamBlock.forward(); updated model.py for compatibility Aashish Dhawan 2025-02-25 15:51:26 -0500
  • c6b8e9662e nit huchenlei 2025-02-25 11:16:52 -0500
  • 446d7be8cc Add type hint for FileLocator huchenlei 2025-02-25 11:13:38 -0500
  • f40076096e Cleanup some lumina te code. comfyanonymous 2025-02-25 04:10:26 -0500
  • b0f756270c
    new file endpoints("v1") to use query parameters instead of path parameters bigcat88 2025-02-25 08:26:50 +0200
  • c4d8766733
    Update README.md Yoland Yan 2025-02-24 19:29:27 -0800
  • 605893d3cf Merge branch 'master' into worksplit-multigpu Jedrzej Kosinski 2025-02-24 19:23:16 -0600
  • 96d891cb94 Speedup on some models by not upcasting bfloat16 to float32 on mac. comfyanonymous 2025-02-24 05:41:07 -0500
  • 4553891bbd
    Update installation documentation to include desktop + cli. (#6899) Robin Huang 2025-02-23 16:13:39 -0800
  • ace899e71a Prioritize fp16 compute when using allow_fp16_accumulation comfyanonymous 2025-02-23 04:45:54 -0500
  • 4a20342fa3
    Create python-app.yml archangelv222 2025-02-23 00:47:56 -0500
  • 457abd2ca7 remove unused params Terry Jia 2025-02-23 00:15:43 -0500
  • 19393de082 Update Fejér Gergely András 2025-02-22 13:18:22 +0000
  • aff16532d4 Remove some useless code. comfyanonymous 2025-02-22 04:45:14 -0500
  • b50ab153f9 Bump ComfyUI version to v0.3.15 v0.3.15 comfyanonymous 2025-02-21 20:28:28 -0500
  • 072db3bea6 Assume the mac black image bug won't be fixed before v16. comfyanonymous 2025-02-21 20:24:07 -0500
  • a6deca6d9a Latest mac still has the black image bug. comfyanonymous 2025-02-21 20:14:30 -0500
  • 01110de8a3 Add tests for delete & update model_management pythongosssss 2025-02-21 17:54:14 +0000
  • 41c30e92e7 Let all model memory be offloaded on nvidia. comfyanonymous 2025-02-21 06:32:11 -0500
  • f579a740dd
    Update frontend release schedule in README. (#6908) filtered 2025-02-21 21:58:12 +1100
  • 9111457d51
    Update frontend release schedule in README. webfiltered-patch-1 filtered 2025-02-21 17:46:09 +1100
  • 1353129f0c Move cli further down. Robin Huang 2025-02-20 20:32:36 -0800
  • 30de8610c5
    temp SGhuge966 2025-02-20 20:16:01 -0800
  • 38ed808658
    fix the bug 'Linear' object has no attribute 'weight_function' qiaoce 2025-02-21 09:13:19 +0800
  • d37272532c
    Add discord channel to support section. (#6900) Robin Huang 2025-02-20 15:26:16 -0800
  • c458eb9640 Add discord channel to support section. Robin Huang 2025-02-20 14:32:32 -0800
  • 43f849d0e7 Add portable to description. Robin Huang 2025-02-20 14:19:35 -0800
  • 47117a684d Update installation documentation. Robin Huang 2025-02-20 14:15:25 -0800
  • 12da6ef581 Apparently directml supports fp16. comfyanonymous 2025-02-20 09:29:59 -0500
  • 29d4384a75
    Normalize extra_model_config.yaml paths to prevent duplicates. (#6885) Robin Huang 2025-02-20 04:09:45 -0800
  • c5be423d6b
    Fix link pointing to non-exisiting docs (#6891) Silver 2025-02-20 13:07:07 +0100
  • bfbad3b554
    Update node_typing.py Silver 2025-02-20 10:54:01 +0100
  • 871dcc6cfe
    Fix link pointing to non-exisiting docs Silver 2025-02-20 10:37:55 +0100
  • cc9d669c62
    fix a bug:AttributeError: 'Linear' object has no attribute 'weight_function' qiaoce 2025-02-20 09:22:12 +0800
  • 51da0256f6 Fix tests. Robin Huang 2025-02-19 15:40:21 -0800
  • a0930eda6d Fix tests. Robin Huang 2025-02-19 15:28:14 -0800
  • 5a78006712 Normalize extra_model_config.yaml paths before adding. Robin Huang 2025-02-19 15:10:58 -0800
  • b4d3652d88
    fixed: crash caused by outdated incompatible aiohttp dependency (#6841) Dr.Lt.Data 2025-02-19 21:15:36 +0900
  • 5715be2ca9
    Fix Hunyuan unet config detection for some models. (#6877) maedtb 2025-02-19 07:14:45 -0500
  • 0d4d9222c6 Add early experimental SaveWEBM node to save .webm files. comfyanonymous 2025-02-19 07:11:49 -0500
  • 305e5d6144
    Fix Hunyuan unet config detection for some models. maedtb 2025-02-19 06:32:44 -0500
  • 483684c103
    Fix failing ffmpeg extension import Windows. Silver 2025-02-19 08:55:39 +0100
  • afc85cdeb6
    Add Load Image Output node (#6790) bymyself 2025-02-18 15:53:01 -0700
  • acc152b674
    Support loading and using SkyReels-V1-Hunyuan-I2V (#6862) Jukka Seppänen 2025-02-19 00:06:54 +0200
  • 47041cc91b Proper latent scaling kijai 2025-02-18 22:10:12 +0200
  • 447ad0442a Fix T2V kijai 2025-02-18 21:21:16 +0200
  • 7d9f51753b VAE scaling kijai 2025-02-18 17:02:11 +0200
  • f8169ace7a Support SkyReels-V1-Hunyuan-I2V kijai 2025-02-18 16:56:00 +0200
  • b07258cef2 Fix typo. comfyanonymous 2025-02-18 07:28:33 -0500
  • 048f4f0b3a Merge branch 'master' into worksplit-multigpu Jedrzej Kosinski 2025-02-17 19:35:58 -0600
  • 857efe645c fixed: crash caused by outdated incompatible aiohttp dependency Dr.Lt.Data 2025-02-17 20:56:01 +0900
  • 31e54b7052 Improve AMD arch detection. comfyanonymous 2025-02-17 04:53:40 -0500
  • 8c0bae50c3 bf16 manual cast works on old AMD. comfyanonymous 2025-02-17 04:42:40 -0500
  • 530412cb9d Refactor torch version checks to be more future proof. comfyanonymous 2025-02-17 04:36:45 -0500
  • 25856a45a4
    add Step-Video Yuan-Man 2025-02-17 17:23:28 +0800
  • 61c8c70c6e
    support system prompt and cfg renorm in Lumina2 (#6795) Zhong-Yu Li 2025-02-17 07:15:43 +0800
  • e8e5496b4d feat(nodes.py): Add support for alpha channel output in LoadImage node dzqdzq 2025-02-17 01:50:14 +0800
  • 785a220757 refactor, adding tests pythongosssss 2025-02-16 17:22:48 +0000
  • d0399f4343
    Update frontend to v1.9.18 (#6828) Comfy Org PR Bot 2025-02-17 01:45:47 +0900
  • 125b27bcb7 Update frontend to v1.9.18 huchenlei 2025-02-16 15:01:55 +0000
  • 1c4bbc2c53 fix issues with the ruff style check lzyhha 2025-02-16 11:43:04 +0000
  • e2919d38b4 Disable bf16 on AMD GPUs that don't support it. comfyanonymous 2025-02-16 05:45:08 -0500
  • 93c8607d51
    remove light_intensity and fov from load3d (#6742) Terry Jia 2025-02-15 15:34:36 -0500
  • b033f1ad43 7z: max compression Margen67 2025-02-15 03:32:39 -0800
  • 77759ef62e Formatting/cleanup Margen67 2025-02-15 02:48:18 -0800
  • 967b0b6aa6 Update actions Margen67 2025-02-14 21:45:59 -0800
  • e15af7951b Indentation Margen67 2025-02-14 21:42:51 -0800
  • d739ea3901 Remove whitespace Margen67 2025-02-14 21:05:37 -0800
  • 346de7b1a1 embeded > embedded Margen67 2025-02-14 20:36:27 -0800
  • b3d6ae15b3
    Update frontend to v1.9.17 (#6814) Comfy Org PR Bot 2025-02-15 18:32:47 +0900
  • 2e21122aab Add a node to set the model compute dtype for debugging. comfyanonymous 2025-02-15 04:15:37 -0500
  • a476e4c5e5 fixed: An issue where the workflows path is not created if it does not exist in the user directory. Dr.Lt.Data 2025-02-15 16:34:30 +0900
  • 05c77dbf09 [Edited] Fix minor bug in the main function MayureshMore 2025-02-14 18:52:34 -0800
  • 3dbb563917 Update frontend to v1.9.17 huchenlei 2025-02-14 18:59:58 +0000
  • 1cd6cd6080 Disable pytorch attention in VAE for AMD. comfyanonymous 2025-02-14 05:42:14 -0500
  • d7b4bf21a2 Auto enable mem efficient attention on gfx1100 on pytorch nightly 2.7 comfyanonymous 2025-02-14 04:17:56 -0500
  • 8ced266669 add except for SystemExit duanyhzi 2025-02-14 06:59:59 +0000
  • 6716679940 Added comfy_base_path and multiple subpaths that are not affected by base_directory Martial Michel 2025-02-13 21:04:32 -0500