Commit Graph

Select branches

Hide Pull Requests

master

Mono Color

• 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
• 93292bc450 ComfyUI version 0.3.29 comfyanonymous 2025-04-17 14:45:01 -04:00
• 05d5a75cdc Update frontend to 1.16 (Install templates as pip package) (#7623) Christian Byrne 2025-04-18 02:25:33 +08:00
• eba7a25e7a Add WanFirstLastFrameToVideo node to use the new model. comfyanonymous 2025-04-17 13:18:43 -04:00
• dbcfd092a2 Set default context_img_len to 257 comfyanonymous 2025-04-17 12:42:34 -04:00
• c14429940f Support loading WAN FLF model. comfyanonymous 2025-04-17 12:04:48 -04:00
• 0d720e4367 Don't hardcode length of context_img in wan code. comfyanonymous 2025-04-17 06:25:39 -04:00
• 1fc00ba4b6 Make hidream work with any latent resolution. comfyanonymous 2025-04-16 18:34:14 -04:00
• 9899d187b1 Limit T5 to 128 tokens for HiDream: #7620 comfyanonymous 2025-04-16 18:07:55 -04:00
• f00f340a56 Reuse code from flux model. comfyanonymous 2025-04-16 17:43:55 -04:00
• cce1d9145e [Type] Mark input options NotRequired (#7614) Chenlei Hu 2025-04-16 15:41:00 -04:00
• b4dc03ad76 Fix issue on old torch. comfyanonymous 2025-04-16 04:53:56 -04:00
• 9ad792f927 Basic support for hidream i1 model. comfyanonymous 2025-04-15 17:35:05 -04:00
• 6fc5dbd52a Cleanup. comfyanonymous 2025-04-15 12:13:28 -04:00
• 3e8155f7a3 More flexible long clip support. comfyanonymous 2025-04-15 10:32:21 -04:00
• 8a438115fb add RMSNorm to comfy.ops comfyanonymous 2025-04-14 18:00:33 -04:00
• a14c2fc356 ComfyUI version v0.3.28 comfyanonymous 2025-04-13 12:21:12 -07:00
• 9ee6ca99d8 add_optimalsteps (#7584) JNP 2025-04-13 08:33:36 +08:00
• bb495cc9b8 Print python version in log. comfyanonymous 2025-04-12 18:58:20 -04:00
• e51d9ba5fc Add SEEDS (stage 2 & 3 DP) sampler (#7580) chaObserv 2025-04-13 06:36:08 +08:00
• c87a06f934 Update filter_files_content_types to support filtering 3d models (#7572) Christian Byrne 2025-04-13 06:30:39 +08:00
• 1714a4c158 Add CublasOps support (#7574) catboxanon 2025-04-12 18:29:15 -04:00
• 73ecb75a3d filter image files in load image dropdown (#7573) Christian Byrne 2025-04-13 06:27:59 +08:00
• 22ad513c72 Refactor node cache code to more easily add other types of cache. comfyanonymous 2025-04-11 07:16:52 -04:00
• ed945a1790 Dependency Aware Node Caching for low RAM/VRAM machines (#7509) Chargeuk 2025-04-11 11:55:51 +01:00
• f9207c6936 Update frontend to 1.15 (#7564) Chenlei Hu 2025-04-11 06:46:20 -04:00
• 8ad7477647 dont cache templates index (#7569) Christian Byrne 2025-04-11 18:06:53 +08:00
• 98bdca4cb2 Deprecate InputTypeOptions.defaultInput (#7551) Chenlei Hu 2025-04-10 06:57:06 -04:00
• a26da20a76 Fix custom nodes not importing when path contains a dot. comfyanonymous 2025-04-10 03:37:27 -04:00
• e346d8584e Add prepare_sampling wrapper allowing custom nodes to more accurately report noise_shape (#7500) Jedrzej Kosinski 2025-04-09 21:43:35 +08:00
• ab31b64412 Make "surface net" the default in the VoxelToMesh node. comfyanonymous 2025-04-09 09:42:08 -04:00
• fe29739c68 add VoxelToMesh node w/ surfacenet meshing (#7446) thot experiment 2025-04-09 06:41:03 -07:00
• e8345a9b7b Align /prompt response schema (#7423) Chenlei Hu 2025-04-09 09:10:36 -04:00
• 8c6b9f4481 Prevent custom nodes from accidentally overwriting global modules. (#7167) comfyanonymous 2025-04-09 09:08:57 -04:00
• cc7e023a4a handle palette mode in loadimage node (#7539) Christian Byrne 2025-04-09 21:07:07 +08:00
• 2f7d8159c3 Show the user an error when the controlnet file is invalid. comfyanonymous 2025-04-08 08:11:59 -04:00
• 70d7242e57 Support the wan fun reward loras. comfyanonymous 2025-04-07 05:01:47 -04:00
• 49b732afd5 Show a proper error to the user when a vision model file is invalid. comfyanonymous 2025-04-06 22:43:56 -04:00
• 3bfe4e5276 Support 512 siglip model. comfyanonymous 2025-04-05 06:14:10 -04:00
• 89e4ea0175 Add activations_shape info in UNet models (#7482) Raphael Walker 2025-04-05 03:27:54 +02:00
• 3a100b9a55 Disable partial offloading of audio VAE. comfyanonymous 2025-04-04 21:24:56 -04:00
• 721253cb05 Fix problem. comfyanonymous 2025-04-03 20:57:59 -04:00
• 3d2e3a6f29 Fix alpha image issue in more nodes. comfyanonymous 2025-04-02 19:32:34 -04:00
• 2222cf67fd MLU memory optimization (#7470) BiologicalExplosion 2025-04-03 07:24:04 +08:00
• ab5413351e Fix comment. comfyanonymous 2025-04-01 14:09:31 -04:00
• 2b71aab299 User missing (#7439) Laurent Erignoux 2025-04-02 01:53:52 +08:00
• 301e26b131 Add option to store TE in bf16 (#7461) BVH 2025-04-01 23:18:53 +05:30
• 548457bac4 Fix alpha channel mismatch on destination in ImageCompositeMasked comfyanonymous 2025-03-31 20:59:12 -04:00
• 0b4584c741 Fix latent composite node not working when source has alpha. comfyanonymous 2025-03-30 21:47:05 -04:00
• a3100c8452 Remove useless code. comfyanonymous 2025-03-29 20:11:43 -04:00
• 832fc02330 ltxv: fix preprocessing exception when compression is 0. (#7431) Michael Kupchick 2025-03-30 03:03:02 +03:00
• 2d17d8910c Don't error if wan concat image has extra channels. comfyanonymous 2025-03-28 08:40:25 -04:00
• a40fcfc2d5 Update frontend to 1.14.6 (#7416) Chenlei Hu 2025-03-28 02:27:01 -04:00
• 0a1f8869c9 Add WanFunInpaintToVideo node for the Wan fun inpaint models. comfyanonymous 2025-03-27 11:13:27 -04:00
• 3661c833bc Support the WAN 2.1 fun control models. comfyanonymous 2025-03-26 19:54:54 -04:00
• 84fdaf7b0e Add CFGZeroStar node. comfyanonymous 2025-03-26 05:08:49 -04:00
• 8edc1f44c1 Support more float8 types. comfyanonymous 2025-03-25 05:23:49 -04:00
• eade1551bb Add Hunyuan3D to readme. comfyanonymous 2025-03-24 07:14:32 -04:00
• 581a9991ff Add model merging node for WAN 2.1 comfyanonymous 2025-03-23 08:06:36 -04:00
• e471c726e5 Fallback to pytorch attention if sage attention fails. comfyanonymous 2025-03-22 15:45:56 -04:00
• 75c1c757d9 ComfyUI version v0.3.27 comfyanonymous 2025-03-21 20:09:54 -04:00
• ce9b084279 [nit] Format error strings (#7345) Chenlei Hu 2025-03-21 19:08:25 -04:00
• 2206246055 support output normal and lineart once (#7290) Terry Jia 2025-03-21 16:24:13 -04:00
• d9fa9d307f Automatically set the right sampling type for lotus. comfyanonymous 2025-03-21 14:19:37 -04:00
• 83e839a89b Native LotusD Implementation (#7125) thot experiment 2025-03-21 11:04:15 -07:00
• 0cf2274699 Update frontend to 1.14 (#7343) Chenlei Hu 2025-03-21 13:50:09 -04:00
• 0956107170 Nodes to convert images to YUV and back. comfyanonymous 2025-03-21 06:32:20 -04:00
• a4a956dbbd Add backend primitive nodes (#7328) Chenlei Hu 2025-03-21 01:47:18 -04:00
• 8b9ce4ed18 Update frontend to 1.13 (#7331) Chenlei Hu 2025-03-21 00:17:36 -04:00
• 3872b43d4b A few fixes for the hunyuan3d models. comfyanonymous 2025-03-20 04:52:31 -04:00
• 32ca0805b7 Fix orientation of hunyuan 3d model. comfyanonymous 2025-03-19 19:55:24 -04:00
• 11f1b41bab Initial Hunyuan3Dv2 implementation. comfyanonymous 2025-03-19 16:19:50 -04:00
• 3b19fc76e3 Allow disabling pe in flux code for some other models. comfyanonymous 2025-03-18 05:09:25 -04:00
• 50614f1b79 Fix regression with clip vision. comfyanonymous 2025-03-17 13:56:11 -04:00
• 6dc7b0bfe3 Add support for giant dinov2 image encoder. comfyanonymous 2025-03-17 05:53:54 -04:00
• e8e990d6b8 Cleanup code. comfyanonymous 2025-03-16 06:29:12 -04:00
• 2e24a15905 Call unpatch_hooks at the start of ModelPatcher.partially_unload (#7253) Jedrzej Kosinski 2025-03-16 05:02:45 -05:00
• fd5297131f Guard the edge cases of noise term in er_sde (#7265) chaObserv 2025-03-16 18:02:25 +08:00
• 55a1b09ddc Allow loading diffusion model files with the "Load Checkpoint" node. comfyanonymous 2025-03-15 08:27:49 -04:00
• 3c3988df45 Show a better error message if the VAE is invalid. comfyanonymous 2025-03-15 08:26:36 -04:00