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

Commit Graph

  • 234c3dc85f Bump frontend to 1.32.9 (#10867) Christian Byrne 2025-11-26 11:58:08 -08:00
  • 8908ee2628 fix(gemini): use first 10 images as fileData (URLs) and remaining images as inline base64 (#10918) Alexander Piskun 2025-11-26 20:38:30 +02:00
  • 1105e0d139 improve UX for batch uploads in upload_images_to_comfyapi (#10913) Alexander Piskun 2025-11-26 19:23:14 +02:00
  • 8938aa3f30 add Veo3 First-Last-Frame node (#10878) Alexander Piskun 2025-11-26 19:14:02 +02:00
  • f16219e3aa Add cheap latent preview for flux 2. (#10907) comfyanonymous 2025-11-26 01:00:43 -08:00
  • 8402c8700a ComfyUI version v0.3.75 comfyanonymous 2025-11-26 02:41:13 -05:00
  • 58b8574661 Fix Flux2 reference image mem estimation. (#10905) comfyanonymous 2025-11-25 23:36:19 -08:00
  • 90b3995ec8 ComfyUI v0.3.74 comfyanonymous 2025-11-26 00:34:15 -05:00
  • bdb10a583f Fix loras not working on mixed fp8. (#10899) comfyanonymous 2025-11-25 21:07:58 -08:00
  • 0e24dbb19f Adjustments to Z Image. (#10893) comfyanonymous 2025-11-25 16:02:51 -08:00
  • e9aae31fa2 Z Image model. (#10892) comfyanonymous 2025-11-25 15:41:45 -08:00
  • 0c18842acb ComfyUI v0.3.73 comfyanonymous 2025-11-25 14:59:37 -05:00
  • d196a905bb Lower vram usage for flux 2 text encoder. (#10887) comfyanonymous 2025-11-25 11:58:39 -08:00
  • 18b79acba9 Update workflow templates to v0.7.20 (#10883) ComfyUI Wiki 2025-11-26 03:58:21 +08:00
  • dff996ca39 Fix crash. (#10885) comfyanonymous 2025-11-25 11:30:24 -08:00
  • 828b1b9953 ComfyUI version v0.3.72 comfyanonymous 2025-11-25 12:40:58 -05:00
  • af81cb962d Add Flux 2 support to README. (#10882) comfyanonymous 2025-11-25 08:40:32 -08:00
  • 5c7b08ca58 [API Nodes] add Flux.2 Pro node (#10880) Alexander Piskun 2025-11-25 18:09:07 +02:00
  • 6b573ae0cb Flux 2 (#10879) comfyanonymous 2025-11-25 07:50:19 -08:00
  • 015a0599d0 I found a case where this is needed (#10875) comfyanonymous 2025-11-25 00:23:19 -08:00
  • acfaa5c4a1 Don't try fp8 matrix mult in quantized ops if not supported by hardware. (#10874) comfyanonymous 2025-11-24 23:55:49 -08:00
  • b6805429b9 Allow pinning quantized tensors. (#10873) comfyanonymous 2025-11-24 23:48:20 -08:00
  • 25022e0b09 Cleanup and fix issues with text encoder quants. (#10872) comfyanonymous 2025-11-24 22:48:53 -08:00
  • 22a2644e57 Bump transformers version in requirements.txt (#10869) comfyanonymous 2025-11-24 16:45:54 -08:00
  • b2ef58e2b1 block info (#10844) Haoming 2025-11-25 02:40:09 +08:00
  • 6a6d456c88 block info (#10842) Haoming 2025-11-25 02:38:38 +08:00
  • 3d1fdaf9f4 block info (#10843) Haoming 2025-11-25 02:30:40 +08:00
  • 1286fcfe40 add get_frame_count and get_frame_rate methods to VideoInput class (#10851) Alexander Piskun 2025-11-24 20:24:29 +02:00
  • 3bd71554a2 fix(api-nodes): edge cases in responses for Gemini models (#10860) Alexander Piskun 2025-11-24 19:48:37 +02:00
  • f66183a541 [fix] Fixes non-async public API access (#10857) guill 2025-11-23 22:56:20 -08:00
  • cbd68e3d58 Add better error message for common error. (#10846) comfyanonymous 2025-11-23 01:55:22 -08:00
  • d89c29f259 Add display names to Hunyuan latent video nodes. (#10837) comfyanonymous 2025-11-22 19:51:53 -08:00
  • a9c35256bc Update requirements.txt (#10834) Christian Byrne 2025-11-22 02:28:29 -08:00
  • 532938b16b --disable-api-nodes now sets CSP header to force frontend offline. (#10829) comfyanonymous 2025-11-21 14:51:55 -08:00
  • ecb683b057 update frontend to 1.30 (#10793) Christian Byrne 2025-11-21 13:34:47 -08:00
  • c55fd74816 ComfyUI 0.3.71 comfyanonymous 2025-11-21 00:49:13 -05:00
  • 3398123752 Fix wrong path. (#10821) comfyanonymous 2025-11-20 20:39:37 -08:00
  • 943b3b615d HunyuanVideo 1.5 (#10819) comfyanonymous 2025-11-20 19:44:43 -08:00
  • 10e90a5757 bump comfyui-workflow-templates for nano banana 2 (#10818) Christian Byrne 2025-11-20 18:20:52 -08:00
  • b75d349f25 fix(KlingLipSyncAudioToVideoNode): convert audio to mp3 format (#10811) Alexander Piskun 2025-11-21 02:33:54 +02:00
  • 7b8389578e feat(api-nodes): add Nano Banana Pro (#10814) Alexander Piskun 2025-11-21 02:17:47 +02:00
  • 9e00ce5b76 Make Batch Images node add alpha channel when one of the inputs has it (#10816) Jedrzej Kosinski 2025-11-20 14:42:46 -08:00
  • f5e66d5e47 Fix ImageBatch with different channel count. (#10815) comfyanonymous 2025-11-20 12:08:03 -08:00
  • 87b0359392 Update server templates handler to use new multi-package distribution (comfyui-workflow-templates versions >=0.3) (#10791) Christian Byrne 2025-11-19 22:36:56 -08:00
  • cb96d4d18c Disable workaround on newer cudnn. (#10807) comfyanonymous 2025-11-19 20:56:23 -08:00
  • 394348f5ca feat(api-nodes): add Topaz API nodes (#10755) Alexander Piskun 2025-11-20 03:44:04 +02:00
  • 7601e89255 Fix workflow name. (#10806) comfyanonymous 2025-11-19 17:17:15 -08:00
  • 6a1d3a1ae1 convert hunyuan3d.py to V3 schema (#10664) Alexander Piskun 2025-11-20 00:49:01 +02:00
  • 65ee24c978 change display name of PreviewAny node to "Preview as Text" (#10796) Alexander Piskun 2025-11-19 11:25:28 +02:00
  • 17027f2a6a Add a way to disable the final norm in the llama based TE models. (#10794) comfyanonymous 2025-11-18 19:36:03 -08:00
  • b5c8be8b1d ComfyUI 0.3.70 comfyanonymous 2025-11-18 19:37:20 -05:00
  • 24fdb92edf feat(api-nodes): add new Gemini model (#10789) Alexander Piskun 2025-11-19 00:26:44 +02:00
  • d526974576 Fix hunyuan 3d 2.0 (#10792) comfyanonymous 2025-11-18 13:46:19 -08:00
  • e1ab6bb394 EasyCache: Fix for mismatch in input/output channels with some models (#10788) Jukka Seppänen 2025-11-18 17:00:21 +02:00
  • 048f49adbd chore(api-nodes): adjusted PR template; set min python version for pylint to 3.10 (#10787) Alexander Piskun 2025-11-18 13:59:27 +02:00
  • 47bfd5a33f Native block swap custom nodes considered harmful. (#10783) comfyanonymous 2025-11-17 21:26:44 -08:00
  • fdf49a2861 Fix the portable download link for CUDA 12.6 (#10780) ComfyUI Wiki 2025-11-18 11:04:06 +08:00
  • f41e5f398d Update README with new portable download link (#10778) comfyanonymous 2025-11-17 16:59:19 -08:00
  • 27cbac865e Add release workflow for NVIDIA cu126 (#10777) comfyanonymous 2025-11-17 16:04:04 -08:00
  • 3d0003c24c ComfyUI version 0.3.69 comfyanonymous 2025-11-17 17:17:24 -05:00
  • 7d6103325e Change ROCm nightly install command to 7.1 (#10764) comfyanonymous 2025-11-16 00:01:14 -08:00
  • 2d4a08b717 Revert "chore(api-nodes): mark OpenAIDalle2 and OpenAIDalle3 nodes as deprecated (#10757)" (#10759) Alexander Piskun 2025-11-15 22:37:34 +02:00
  • 9a02382568 chore(api-nodes): mark OpenAIDalle2 and OpenAIDalle3 nodes as deprecated (#10757) Alexander Piskun 2025-11-15 21:18:49 +02:00
  • bd01d9f7fd Add left padding support to tokenizers. (#10753) comfyanonymous 2025-11-15 03:54:40 -08:00
  • 443056c401 Fix custom nodes import error. (#10747) comfyanonymous 2025-11-14 00:26:05 -08:00
  • f60923590c Use same code for chroma and flux blocks so that optimizations are shared. (#10746) comfyanonymous 2025-11-13 22:28:05 -08:00
  • 1ef328c007 Better instructions for the portable. (#10743) comfyanonymous 2025-11-13 18:32:39 -08:00
  • 94c298f962 flux: reduce VRAM usage (#10737) rattus 2025-11-14 10:02:03 +10:00
  • 2fde9597f4 feat: add create_time dict to prompt field in /history and /queue (#10741) ric-yu 2025-11-13 15:11:52 -08:00
  • f91078b1ff add PR template for API-Nodes (#10736) Alexander Piskun 2025-11-13 20:05:26 +02:00
  • 3b3ef9a77a Quantized Ops fixes (#10715) contentis 2025-11-13 00:26:52 +01:00
  • 8b0b93df51 Update Python 3.14 compatibility notes in README (#10730) comfyanonymous 2025-11-12 14:04:41 -08:00
  • 1c7eaeca10 qwen: reduce VRAM usage (#10725) rattus 2025-11-13 07:20:53 +10:00
  • 18e7d6dba5 mm/mp: always unload re-used but modified models (#10724) rattus 2025-11-13 07:19:53 +10:00
  • e1d85e7577 Update README.md for Intel Arc GPU installation, remove IPEX (#10729) Qiacheng Li 2025-11-12 12:21:05 -08:00
  • 1199411747 Don't pin tensor if not a torch.nn.parameter.Parameter (#10718) comfyanonymous 2025-11-11 16:33:30 -08:00
  • 5ebcab3c7d Update CI workflow to remove dead macOS runner. (#10704) comfyanonymous 2025-11-10 12:35:29 -08:00
  • c350009236 ops: Put weight cast on the offload stream (#10697) rattus 2025-11-10 13:52:11 +10:00
  • dea899f221 Unload weights if vram usage goes up between runs. (#10690) comfyanonymous 2025-11-09 15:51:33 -08:00
  • e632e5de28 Add logging for model unloading. (#10692) comfyanonymous 2025-11-09 15:06:39 -08:00
  • 2abd2b5c20 Make ScaleROPE node work on Flux. (#10686) comfyanonymous 2025-11-08 12:52:02 -08:00
  • a1a70362ca Only unpin tensor if it was pinned by ComfyUI (#10677) comfyanonymous 2025-11-07 08:15:05 -08:00
  • cf97b033ee mm: guard against double pin and unpin explicitly (#10672) rattus 2025-11-07 12:20:48 +10:00
  • eb1c42f649 Tell users they need to upload their logs in bug reports. (#10671) comfyanonymous 2025-11-06 17:24:28 -08:00
  • e05c907126 Clarify release cycle. (#10667) comfyanonymous 2025-11-06 01:11:30 -08:00
  • 09dc24c8a9 Pinned mem also seems to work on AMD. (#10658) comfyanonymous 2025-11-05 16:11:15 -08:00
  • 1d69245981 Enable pinned memory by default on Nvidia. (#10656) comfyanonymous 2025-11-05 15:08:13 -08:00
  • 97f198e421 Fix qwen controlnet regression. (#10657) comfyanonymous 2025-11-05 15:07:35 -08:00
  • bda0eb2448 feat(API-nodes): move Rodin3D nodes to new client; removed old api client.py (#10645) Alexander Piskun 2025-11-05 12:16:00 +02:00
  • c4a6b389de Lower ltxv mem usage to what it was before previous pr. (#10643) comfyanonymous 2025-11-04 19:47:35 -08:00
  • 4cd881866b Use single apply_rope function across models (#10547) contentis 2025-11-05 02:10:11 +01:00
  • 265adad858 ComfyUI version v0.3.68 comfyanonymous 2025-11-04 19:42:23 -05:00
  • 7f3e4d486c Limit amount of pinned memory on windows to prevent issues. (#10638) comfyanonymous 2025-11-04 14:37:50 -08:00
  • a389ee01bb caching: Handle None outputs tuple case (#10637) rattus 2025-11-05 08:14:10 +10:00
  • 9c71a66790 chore: update workflow templates to v0.2.11 (#10634) ComfyUI Wiki 2025-11-05 02:51:53 +08:00
  • af4b7b5edb More fp8 torch.compile regressions fixed. (#10625) comfyanonymous 2025-11-03 19:14:20 -08:00
  • 0f4ef3afa0 This seems to slow things down slightly on Linux. (#10624) comfyanonymous 2025-11-03 18:47:14 -08:00
  • 6b88478f9f Bring back fp8 torch compile performance to what it should be. (#10622) comfyanonymous 2025-11-03 16:22:10 -08:00
  • e199c8cc67 Fixes (#10621) comfyanonymous 2025-11-03 14:58:24 -08:00
  • 0652cb8e2d Speed up torch.compile (#10620) comfyanonymous 2025-11-03 14:37:12 -08:00