Commit Graph

  • 5c33872e2f Fix issue on old torch. (#9791) comfyanonymous 2025-09-09 21:23:47 -07:00
  • 206595f854 Change validate_inputs' output typehint to 'bool | str' and update docstrings (#9786) Jedrzej Kosinski 2025-09-09 18:33:36 -07:00
  • b288fb0db8 Small refactor of some vae code. (#9787) comfyanonymous 2025-09-09 15:09:56 -07:00
  • f73b176abd add ByteDance video API nodes (#9712) Alexander Piskun 2025-09-09 21:40:29 +03:00
  • 103a12cb66 Support qwen inpaint controlnet. (#9772) comfyanonymous 2025-09-08 14:30:26 -07:00
  • 97652d26b8 Add explicit casting in apply_rope for Qwen VL (#9759) contentis 2025-09-08 21:08:18 +02:00
  • bd1d9bcd5f Add ZeroDivisionError catch for EasyCache logging statement (#9768) Jedrzej Kosinski 2025-09-08 12:07:04 -07:00
  • fb763d4333 Fix amd_min_version crash when cpu device. (#9754) comfyanonymous 2025-09-07 18:16:29 -07:00
  • bcbd7884e3 Don't enable pytorch attention on AMD if triton isn't available. (#9747) comfyanonymous 2025-09-06 21:29:38 -07:00
  • 27a0fcccc3 Enable bf16 VAE on RDNA4. (#9746) comfyanonymous 2025-09-06 20:25:22 -07:00
  • ea6cdd2631 Print all fast options in --help (#9737) comfyanonymous 2025-09-05 22:05:05 -07:00
  • 2ee7879a0b Fix lowvram issues with hunyuan3d 2.1 (#9735) comfyanonymous 2025-09-05 11:57:35 -07:00
  • 3493b9cb1f fix: add cache headers for images (#9560) Arjan Singh 2025-09-05 11:32:25 -07:00
  • c9ebe70072 Some changes to the previous hunyuan PR. (#9725) comfyanonymous 2025-09-04 17:39:02 -07:00
  • 261421e218 Add Hunyuan 3D 2.1 Support (#8714) Yousef R. Gamaleldin 2025-09-05 03:36:20 +03:00
  • a9f1bb10a5 Fix progress update crossover between users (#9706) guill 2025-09-04 16:13:28 -07:00
  • b0338e930b ComfyUI 0.3.57 comfyanonymous 2025-09-04 02:15:57 -04:00
  • b71f9bcb71 Update template to 0.1.75 (#9711) ComfyUI Wiki 2025-09-04 14:14:02 +08:00
  • 72855db715 Fix potential rope issue. (#9710) comfyanonymous 2025-09-03 19:20:13 -07:00
  • f48d05a2d1 convert AlignYourStepsScheduler node to V3 schema (#9226) Alexander Piskun 2025-09-04 04:21:38 +03:00
  • 4368d8f87f Update comment in api example. (#9708) comfyanonymous 2025-09-03 15:43:29 -07:00
  • 22da0a83e9 [V3] convert Runway API nodes to the V3 schema (#9487) Alexander Piskun 2025-09-03 23:18:27 +03:00
  • 50333f1715 api nodes(Ideogram): add Ideogram Character (#9616) Alexander Piskun 2025-09-03 23:17:37 +03:00
  • 26d5b86da8 feat(api-nodes): add ByteDance Image nodes (#9477) Alexander Piskun 2025-09-03 23:17:07 +03:00
  • 4f5812b937 Update template to 0.1.73 (#9686) ComfyUI Wiki 2025-09-03 08:06:41 +08:00
  • 1bcb469089 ImageScaleToMaxDimension node. (#9689) comfyanonymous 2025-09-02 17:05:57 -07:00
  • 464ba1d614 Accept prompt_id in interrupt handler (#9607) Deep Roy 2025-09-02 19:41:10 -04:00
  • e3018c2a5a uso -> uxo/uno as requested. (#9688) comfyanonymous 2025-09-02 13:12:07 -07:00
  • 3412d53b1d USO style reference. (#9677) comfyanonymous 2025-09-02 12:36:22 -07:00
  • e2d1e5dad9 Enable Convolution AutoTuning (#9301) contentis 2025-09-02 02:33:50 +02:00
  • 27e067ce50 Implement the USO subject identity lora. (#9674) comfyanonymous 2025-09-01 15:54:02 -07:00
  • 9b15155972 Probably not necessary anymore. (#9646) comfyanonymous 2025-08-30 22:32:10 -07:00
  • 32a627bf1f SEEDS: update noise decomposition and refactor (#9633) chaObserv 2025-08-31 12:01:45 +08:00
  • fe442fac2e convert Primitive nodes to V3 schema (#9372) Alexander Piskun 2025-08-31 06:21:58 +03:00
  • d2c502e629 convert nodes_stability.py to V3 schema (#9497) Alexander Piskun 2025-08-31 06:20:17 +03:00
  • fea9ea8268 convert Video nodes to V3 schema (#9489) Alexander Piskun 2025-08-31 06:19:54 +03:00
  • f949094b3c convert Stable Cascade nodes to V3 schema (#9373) Alexander Piskun 2025-08-31 06:19:21 +03:00
  • 4449e14769 ComfyUI version 0.3.56 comfyanonymous 2025-08-30 06:31:19 -04:00
  • 885015eecf Lower ram usage on windows. (#9628) comfyanonymous 2025-08-29 20:06:04 -07:00
  • a86aaa4301 ComfyUI v0.3.55 comfyanonymous 2025-08-29 05:33:29 -04:00
  • 2efb2cbc38 Update template to 0.1.70 (#9620) ComfyUI Wiki 2025-08-29 18:03:25 +08:00
  • 15aa9222c4 Trim audio to video when saving video. (#9617) comfyanonymous 2025-08-29 01:12:00 -07:00
  • c7bb3e2bce Support the 5B fun inpaint model. (#9614) comfyanonymous 2025-08-28 19:46:57 -07:00
  • e80a14ad50 Support wan2.2 5B fun control model. (#9611) comfyanonymous 2025-08-28 19:13:07 -07:00
  • d28b39d93d Add a LatentCut node to cut latents. (#9609) comfyanonymous 2025-08-28 16:38:28 -07:00
  • 1c184c29eb Fix issue with s2v node when extending past audio length. (#9608) comfyanonymous 2025-08-28 15:34:01 -07:00
  • edde0b5043 WanSoundImageToVideoExtend node to manually extend s2v video. (#9606) comfyanonymous 2025-08-28 14:59:48 -07:00
  • 0063610177 ComfyUI version 0.3.54 comfyanonymous 2025-08-28 10:44:57 -04:00
  • ce0052c087 Fix diffsynth controlnet regression. (#9597) comfyanonymous 2025-08-28 07:37:42 -07:00
  • 0eb821a7b6 ComfyUI 0.3.53 comfyanonymous 2025-08-27 23:09:06 -04:00
  • 4aa79dbf2c Adjust flux mem usage factor a bit. (#9588) comfyanonymous 2025-08-27 20:08:17 -07:00
  • 38f697d953 Add a LatentConcat node. (#9587) comfyanonymous 2025-08-27 19:28:10 -07:00
  • 3aad339b63 Add DPM++ 2M SDE Heun (RES) sampler (#9542) Gangin Park 2025-08-28 08:07:31 +09:00
  • 491755325c Better s2v memory estimation. (#9584) comfyanonymous 2025-08-27 16:02:42 -07:00
  • 496888fd68 Improve s2v performance when generating videos longer than 120 frames. (#9582) comfyanonymous 2025-08-27 13:06:40 -07:00
  • b5ac6ed7ce Fixes to make controlnet type models work on qwen edit and kontext. (#9581) comfyanonymous 2025-08-27 12:26:28 -07:00
  • b20ba1f27c Fix #9537 (#9576) Kohaku-Blueleaf 2025-08-28 00:45:02 +08:00
  • 31a37686d0 Negative audio in s2v should be zeros. (#9578) comfyanonymous 2025-08-27 09:44:29 -07:00
  • 88aee596a3 WIP Wan 2.2 S2V model. (#9568) comfyanonymous 2025-08-26 22:10:34 -07:00
  • 6a193ac557 Update template to 0.1.68 (#9569) ComfyUI Wiki 2025-08-27 12:10:20 +08:00
  • 47f4db3e84 Adding Google Gemini Image API node (#9566) Jedrzej Kosinski 2025-08-26 19:20:44 -07:00
  • 5352abc6d3 Update template to 0.1.66 (#9557) ComfyUI Wiki 2025-08-27 01:33:54 +08:00
  • 39aa06bd5d Make AudioEncoderOutput usable in v3 node schema. (#9554) comfyanonymous 2025-08-26 09:50:46 -07:00
  • 914c2a2973 Implement wav2vec2 as an audio encoder model. (#9549) comfyanonymous 2025-08-25 20:26:47 -07:00
  • e633a47ad1 Add models/audio_encoders directory. (#9548) comfyanonymous 2025-08-25 17:13:54 -07:00
  • f6b93d41a0 Remove models from readme that are not fully implemented. (#9535) comfyanonymous 2025-08-24 12:40:32 -07:00
  • 95ac7794b7 Fix EasyCache/LazyCache crash when tensor shape/dtype/device changes during sampling (#9528) blepping 2025-08-24 13:29:49 -06:00
  • 71ed4a399e ComfyUI version 0.3.52 comfyanonymous 2025-08-23 18:57:09 -04:00
  • 3e316c6338 Update frontend to v1.25.10 and revert navigation mode override (#9522) Christian Byrne 2025-08-23 14:54:01 -07:00
  • 8be0d22ab7 Don't use the annoying new navigation mode by default. (#9518) comfyanonymous 2025-08-23 10:56:17 -07:00
  • 59eddda900 Python 3.13 is well supported. (#9511) comfyanonymous 2025-08-22 22:36:44 -07:00
  • 41048c69b4 Fix Conditioning masks on 3d latents. (#9506) comfyanonymous 2025-08-22 20:15:44 -07:00
  • fc247150fe Implement EasyCache and Invent LazyCache (#9496) Jedrzej Kosinski 2025-08-22 19:41:08 -07:00
  • fe31ad0276 Add elementwise fusions (#9495) contentis 2025-08-23 01:39:15 +02:00
  • ca4e96a8ae Update template to 0.1.65 (#9501) ComfyUI Wiki 2025-08-23 05:40:18 +08:00
  • 050c67323c feat(api-nodes): add copy button to Gemini Chat node (#9440) Alexander Piskun 2025-08-22 20:51:14 +03:00
  • 497d41fb50 feat(api-nodes): change "OpenAI Chat" display name to "OpenAI ChatGPT" (#9443) Alexander Piskun 2025-08-22 20:50:35 +03:00
  • ff57793659 Support InstantX Qwen controlnet. (#9488) comfyanonymous 2025-08-21 21:53:11 -07:00
  • f7bd5e58dd Make it easier to implement future qwen controlnets. (#9485) comfyanonymous 2025-08-21 20:18:04 -07:00
  • 7ed73d12d1 [V3] convert Ideogram API nodes to the V3 schema (#9278) Alexander Piskun 2025-08-22 05:06:51 +03:00
  • eb39019daa [V3] convert Google Veo API node to the V3 schema (#9272) Alexander Piskun 2025-08-22 05:06:13 +03:00
  • bab08f40d1 v3 nodes (part a) (#9149) Alexander Piskun 2025-08-22 05:05:36 +03:00
  • bc49106837 convert String nodes to V3 schema (#9370) Alexander Piskun 2025-08-22 05:03:57 +03:00
  • 1b2de2642d Support diffsynth inpaint controlnet (model patch). (#9471) comfyanonymous 2025-08-20 21:33:49 -07:00
  • 9fa1036f60 Forgot this. (#9470) comfyanonymous 2025-08-20 20:09:35 -07:00
  • 0737b7e0d2 fix(userdata): catch invalid workflow filenames (#9434) (#9445) saurabh-pingale 2025-08-21 07:57:57 +05:30
  • 0963493a9c Support for Qwen Diffsynth Controlnets canny and depth. (#9465) comfyanonymous 2025-08-20 19:26:37 -07:00
  • e73a9dbe30 Add that qwen edit model is supported to readme. (#9463) comfyanonymous 2025-08-20 14:34:13 -07:00
  • fe01885acf LTXV: fix key frame noise mask dimensions for when real noise mask exists (#9425) Harel Cain 2025-08-20 09:33:10 +02:00
  • 7139d6d93f ComfyUI version 0.3.51 comfyanonymous 2025-08-20 03:15:30 -04:00
  • 2f52e8f05f Bump template to 0.1.62 (#9419) ComfyUI Wiki 2025-08-20 15:15:09 +08:00
  • 8d38ea3bbf Fix bf16 precision issue with qwen image embeddings. (#9441) comfyanonymous 2025-08-19 23:58:54 -07:00
  • 5a8f502db5 Disable prompt weights for qwen. (#9438) comfyanonymous 2025-08-19 22:08:11 -07:00
  • 7cd2c4bd6a Qwen rotary embeddings should now match reference code. (#9437) comfyanonymous 2025-08-19 21:45:27 -07:00
  • dfa791eb4b Rope fix for qwen vl. (#9435) comfyanonymous 2025-08-19 17:47:42 -07:00
  • bddd69618b Change the TextEncodeQwenImageEdit node to use logic closer to reference. (#9432) comfyanonymous 2025-08-19 13:49:01 -07:00
  • 54d8fdbed0 feat(api-nodes): add Vidu Video nodes (#9368) Alexander Piskun 2025-08-19 23:30:06 +03:00
  • d844d8b13b api_nodes: added release version of google's models (#9304) Alexander Piskun 2025-08-19 23:29:24 +03:00
  • 07a927517c api_nodes: add GPT-5 series models (#9325) Alexander Piskun 2025-08-19 23:29:01 +03:00
  • f16a70ba67 api_nodes: add MinimaxHailuoVideoNode node (#9262) Alexander Piskun 2025-08-19 23:28:27 +03:00