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

Commit Graph

  • f4bdf5f830 sd: revise hy VAE VRAM (#11105) rattus 2025-12-05 03:50:04 +10:00
  • 6be85c7920 mp: use look-ahead actuals for stream offload VRAM calculation (#11096) rattus 2025-12-04 14:28:44 +10:00
  • ea17add3c6 Fix case where text encoders where running on the CPU instead of GPU. (#11095) comfyanonymous 2025-12-03 20:15:15 -08:00
  • ecdc8697d5 Qwen Image Lora training fix from #11090 (#11094) comfyanonymous 2025-12-03 19:49:28 -08:00
  • dce518c2b4 convert nodes_audio.py to V3 schema (#10798) Alexander Piskun 2025-12-04 03:35:04 +02:00
  • 440268d394 convert nodes_load_3d.py to V3 schema (#10990) Alexander Piskun 2025-12-03 23:52:31 +02:00
  • 87c104bfc1 add support for "@image" reference format in Kling Omni API nodes (#11082) Alexander Piskun 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 Piskun 2025-12-03 18:37:35 +02:00
  • 519c941165 Prs/lora reservations (reduce massive Lora reservations especially on Flux2) (#11069) rattus 2025-12-03 17:28:45 +10:00
  • 861817d22d Fix issue with portable updater. (#11070) comfyanonymous 2025-12-02 21:47:51 -08:00
  • c120eee5ba Add MatchType, DynamicCombo, and Autogrow support to V3 Schema (#10832) Jedrzej Kosinski 2025-12-02 21:17:13 -08:00
  • 59afc39848 ComfyUI v0.3.77 v0.3.77 origin/release/v0.3.77 comfyanonymous 2025-12-03 00:02:09 -05:00
  • 028e17dd7a add check for the format arg type in VideoFromComponents.save_to function (#11046) Alexander Piskun 2025-12-02 21:50:13 +02:00
  • 73f5649196 Implement temporal rolling VAE (Major VRAM reductions in Hunyuan and Kandinsky) (#10995) rattus 2025-12-03 13:49:29 +10:00
  • 3f512f5659 Added PATCH method to CORS headers (#11066) Jim Heising 2025-12-02 19:29:27 -08:00
  • b94d394a64 Support Z Image alibaba pai fun controlnets. (#11062) comfyanonymous 2025-12-02 18:38:31 -08:00
  • 277237ccc1 attention: use flag based OOM fallback (#11038) rattus 2025-12-03 08:24:19 +10:00
  • daaceac769 Hack to make zimage work in fp16. (#11057) comfyanonymous 2025-12-02 14:11:58 -08:00
  • 33d6aec3b7 add check for the format arg type in VideoFromComponents.save_to function (#11046) Alexander Piskun 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 Kosinski 2025-12-02 11:46:29 -08:00
  • a17cf1c387 Add @guill as a code owner (#11031) Yoland Yan 2025-12-01 19:40:44 -08:00
  • b4a20acc54 feat: Support ComfyUI-Manager for pip version (#7555) Dr.Lt.Data 2025-12-02 12:32:52 +09:00
  • c55dc857d5 bump comfyui-frontend-package to 1.33.10 (#11028) Christian Byrne 2025-12-01 17:56:38 -08:00
  • 878db3a727 Implement the Ovis image model. (#11030) comfyanonymous 2025-12-01 17:56:17 -08:00
  • 30c259cac8 ComfyUI version v0.3.76 v0.3.76 comfyanonymous 2025-12-01 20:25:35 -05:00
  • 1cb7e22a95 [API Nodes] add Kling O1 model support (#11025) Alexander Piskun 2025-12-02 02:11:52 +02:00
  • 2640acb31c Update qwen tokenizer to add qwen 3 tokens. (#11029) comfyanonymous 2025-12-01 14:13:48 -08:00
  • 7dbd5dfe91 bump comfyui-frontend-package to 1.32.10 (#11018) Christian Byrne 2025-12-01 10:27:17 -08:00
  • f8b981ae9a Next AMD portable will have pytorch with ROCm 7.1.1 (#11002) comfyanonymous 2025-11-30 01:21:31 -08:00
  • 4967f81778 update template to 0.7.25 (#10996) ComfyUI Wiki 2025-11-30 10:07:26 +08:00
  • 0a6746898d Make the ScaleRope node work on Z Image and Lumina. (#10994) comfyanonymous 2025-11-29 15:00:55 -08:00
  • 5151cff293 Add some missing z image lora layers. (#10980) comfyanonymous 2025-11-28 20:55:00 -08:00
  • af96d9812d feat(security): add System User protection with __ prefix (#10966) Dr.Lt.Data 2025-11-29 11:28:42 +09:00
  • 52a32e2b32 Support some z image lora formats. (#10978) comfyanonymous 2025-11-28 18:12:42 -08:00
  • b907085709 Support video tiny VAEs (#10884) Jukka Seppänen 2025-11-29 02:40:19 +02:00
  • 065a2fbbec Update driver link in AMD portable README (#10974) comfyanonymous 2025-11-28 16:37:39 -08:00
  • 0ff0457892 mm: wrap the raw stream in context manager (#10958) rattus 2025-11-29 07:38:12 +10:00
  • 6484ac89dc fix QuantizedTensor.is_contiguous (#10956) (#10959) Urle Sistiana 2025-11-29 05:33:07 +08:00
  • f55c98a89f Disable offload stream when torch compile. (#10961) comfyanonymous 2025-11-28 13:16:46 -08:00
  • ca7808f240 fix(user_manager): fix typo in move_userdata dest validation (#10967) Dr.Lt.Data 2025-11-29 05:43:17 +09:00
  • 52e778fff3 feat(Kling-API-Nodes): add v2-5-turbo model to FirstLastFrame node (#10938) Alexander Piskun 2025-11-28 12:52:59 +02:00
  • 9d8a817985 Enable async offloading by default on Nvidia. (#10953) comfyanonymous 2025-11-27 14:46:12 -08:00
  • b59750a86a Update template to 0.7.23 (#10949) ComfyUI Wiki 2025-11-28 06:12:56 +08:00
  • 3f382a4f98 quant ops: Dequantize weight in-place (#10935) rattus 2025-11-28 02:06:30 +10:00
  • f17251bec6 Account for the VRAM cost of weight offloading (#10733) rattus 2025-11-27 16:03:03 +10:00
  • c38e7d6599 block info (#10841) Haoming 2025-11-27 12:28:44 +08:00
  • eaf68c9b5b Make lora training work on Z Image and remove some redundant nodes. (#10927) comfyanonymous 2025-11-26 16:25:32 -08:00
  • cc6a8dcd1a Dataset Processing Nodes and Improved LoRA Trainer Nodes with multi resolution supports. (#10708) Kohaku-Blueleaf 2025-11-27 08:18:08 +08:00
  • a2d60aad0f convert nodes_customer_sampler.py to V3 schema (#10206) Alexander Piskun 2025-11-27 00:55:31 +02:00
  • d8433c63fd chore(api-nodes): remove chat widgets from OpenAI/Gemini nodes (#10861) Alexander Piskun 2025-11-27 00:42:01 +02:00
  • dd41b74549 Add Z Image to readme. (#10924) comfyanonymous 2025-11-26 12:36:38 -08:00
  • 55f654db3d Fix the CSP offline feature. (#10923) comfyanonymous 2025-11-26 12:16:40 -08:00
  • 58c6ed541d Merge 3d animation node (#10025) Terry Jia 2025-11-26 14:58:27 -05:00
  • 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 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 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 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 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 v0.3.71 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