Commit Graph

  • f051129c1d
    Merge branch 'comfyanonymous:master' into feature/custom_nodes-envvar Sas van Gulik 2025-11-05 11:51:28 +0100
  • 4a010caa0d change delimiter type for seperate folders per platform. Sasbom 2025-11-05 11:26:11 +0100
  • 764d6c43f3 allow for PATH style ';' delimited custom_node directories. Sasbom 2025-11-05 11:16:59 +0100
  • bda0eb2448
    feat(API-nodes): move Rodin3D nodes to new client; removed old api client.py (#10645) Alexander Piskun 2025-11-05 12:16:00 +0200
  • 84faf45f09
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-05 13:07:02 +0300
  • 7237c36fba Merge remote-tracking branch 'upstream/master' into multitalk kijai 2025-11-05 11:36:07 +0200
  • 90b6ed7d09
    bugfix: fix typo in apply_directory for custom_nodes_directory Sas van Gulik 2025-11-05 09:29:42 +0100
  • 175c22dad4 Merge remote-tracking branch 'origin/sfink-amd-cudnn-envvar' into sfink-amd-cudnn-envvar Christopher Anderson 2025-11-05 18:35:17 +1100
  • 58db8864a6 Add env TORCH_AMD_CUDNN_ENABLED Christopher Anderson 2025-11-05 18:35:00 +1100
  • f9618b7e4b Add QOL feature for changing the custom nodes folder location through cli args or a COMFYUI_CUSTOM_NODES_DIR environment variable. Sasbom 2025-11-05 07:40:32 +0100
  • 242037fa32 Fix EliGen RoPE shape to match apply_rope1() requirements nolan4 2025-11-04 21:55:02 -0800
  • 9792606847 added attention_mask to QwenImageTransformerBlock.forward() nolan4 2025-11-04 19:55:24 -0800
  • 581f8fe930 Also add MatchType check to input_type in validation - will likely trigger when connecting to non-lazy stuff Jedrzej Kosinski 2025-11-04 19:54:28 -0800
  • c4a6b389de
    Lower ltxv mem usage to what it was before previous pr. (#10643) comfyanonymous 2025-11-04 19:47:35 -0800
  • bd78daa9a7 Make match type receive_type pass validation Jedrzej Kosinski 2025-11-04 19:41:14 -0800
  • 62c1e888cd Lower ltxv mem usage to what it was before previous pr. comfyanonymous 2025-11-04 22:40:50 -0500
  • 53c4aab268 Merge branch 'combo-output-fix' into v3-match-type Jedrzej Kosinski 2025-11-04 19:37:44 -0800
  • 152524e8b1 Fix docker image containing random text files in it doctorpangloss 2025-11-04 19:22:26 -0800
  • 7f7bcd5d8f Fix tests (no rerelease necessary) doctorpangloss 2025-11-04 18:33:31 -0800
  • cb97b94ad9 Unclear why this is throwing linting errors doctorpangloss 2025-11-04 18:15:54 -0800
  • 4b336543db Update README.md doctorpangloss 2025-11-04 17:43:22 -0800
  • 98ae55b059 Improvements to compatibility with custom nodes, distributed backends and other changes doctorpangloss 2025-11-04 17:40:19 -0800
  • 4cd881866b
    Use single apply_rope function across models (#10547) contentis 2025-11-05 02:10:11 +0100
  • 7b77a0d305 Add workaround in validation.py for V3 Combo outputs not working as Combo inputs combo-output-fix Jedrzej Kosinski 2025-11-04 16:58:34 -0800
  • 265adad858 ComfyUI version v0.3.68 v0.3.68 comfyanonymous 2025-11-04 19:42:23 -0500
  • e31f7a1128 Fixed providing list of allowed_types Jedrzej Kosinski 2025-11-04 16:06:26 -0800
  • 16adfe2153 restored whitespace and fixed logging nolan4 2025-11-04 15:46:52 -0800
  • 32bd55779a Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-11-05 07:42:29 +0900
  • 7f3e4d486c
    Limit amount of pinned memory on windows to prevent issues. (#10638) comfyanonymous 2025-11-04 14:37:50 -0800
  • 4057540efe Added output_matchtypes to generated json for v3, initial backend support for MatchType, created nodes_logic.py and added SwitchNode Jedrzej Kosinski 2025-11-04 14:30:03 -0800
  • 704d137c90 Limit amount of pinned memory on windows to prevent issues. comfyanonymous 2025-11-04 17:26:29 -0500
  • a389ee01bb
    caching: Handle None outputs tuple case (#10637) rattus 2025-11-05 08:14:10 +1000
  • 78aee2df53 caching: Handle None outputs tuple case Rattus 2025-11-05 08:01:39 +1000
  • 9e9c536c8e fixes from testing Yousef Rafat 2025-11-04 23:55:16 +0200
  • 9c71a66790
    chore: update workflow templates to v0.2.11 (#10634) ComfyUI Wiki 2025-11-05 02:51:53 +0800
  • 6f6781fa4b chore: update workflow templates to v0.2.11 ComfyUI Wiki 2025-11-05 02:41:02 +0800
  • fe28a51589 chore: update workflow templates to v0.2.10 ComfyUI Wiki 2025-11-05 02:14:21 +0800
  • 671a769dc6 Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-11-04 23:25:51 +0900
  • 11083ab58c
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-04 13:09:30 +0300
  • 88746bf3aa Merge branch 'master' into dataset-process-nodes Kohaku-Blueleaf 2025-11-04 17:25:41 +0800
  • 650b7b0302 move all dataset related implementation to nodes_dataset Kohaku-Blueleaf 2025-11-04 12:51:40 +0800
  • 992aa2dd8f allow trainer node to get different resolution dataset Kohaku-Blueleaf 2025-11-04 12:50:25 +0800
  • af4b7b5edb
    More fp8 torch.compile regressions fixed. (#10625) comfyanonymous 2025-11-03 19:14:20 -0800
  • bc3daf25f1 More fp8 torch.compile regressions fixed. comfyanonymous 2025-11-03 22:07:05 -0500
  • 9db1425b70 fix: update folder path logic to use correct module path limon-daohaosisi 2025-11-04 10:58:07 +0800
  • 0f4ef3afa0
    This seems to slow things down slightly on Linux. (#10624) comfyanonymous 2025-11-03 18:47:14 -0800
  • 499f6d8a82
    This seems to slow things down slightly on Linux. comfyanonymous 2025-11-03 21:39:15 -0500
  • 6b88478f9f
    Bring back fp8 torch compile performance to what it should be. (#10622) comfyanonymous 2025-11-03 16:22:10 -0800
  • 34c79a1d38
    Fix recursion. comfyanonymous 2025-11-03 19:15:35 -0500
  • 8230919053
    Remove debug print for tensor shapes comfyanonymous 2025-11-03 19:00:23 -0500
  • 6c84d84a48 Bring back fp8 torch compile performance to what it should be. comfyanonymous 2025-11-03 18:58:19 -0500
  • e199c8cc67
    Fixes (#10621) comfyanonymous 2025-11-03 14:58:24 -0800
  • 3abd66aace
    Fixes comfyanonymous 2025-11-03 17:51:53 -0500
  • 0652cb8e2d
    Speed up torch.compile (#10620) comfyanonymous 2025-11-03 14:37:12 -0800
  • 197d778fdf
    Speed up torch.compile comfyanonymous 2025-11-03 17:33:34 -0500
  • 958a17199a
    People should update their pytorch versions. (#10618) comfyanonymous 2025-11-03 14:08:30 -0800
  • 355c0480fa People should update their pytorch versions. comfyanonymous 2025-11-03 16:41:57 -0500
  • 3ae78a4804 Update model_multitalk.py kijai 2025-11-03 21:13:57 +0200
  • d53e62913d Remove looping functionality, keep extension functionality kijai 2025-11-03 21:12:02 +0200
  • e974e554ca
    chore: update embedded docs to v0.3.1 (#10614) ComfyUI Wiki 2025-11-04 02:59:44 +0800
  • 8d62661a9f Remove LoopingSamplerCustomAdvanced kijai 2025-11-03 20:53:32 +0200
  • 6bfce54652 Move block_idx to transformer_options kijai 2025-11-03 20:53:06 +0200
  • 8771dd51db
    Merge pull request #2 from lmichaelwar/revert-1-stable-horde-integration L Michael War 2025-11-03 13:40:02 -0500
  • e5362d1389
    Revert "feat: Implement Stable Horde as a ComfyUI node" L Michael War 2025-11-03 13:39:43 -0500
  • 3b351633fa
    Merge pull request #1 from lmichaelwar/stable-horde-integration L Michael War 2025-11-03 13:39:35 -0500
  • 536e5a17db feat: Implement Stable Horde as a ComfyUI node google-labs-jules[bot] 2025-11-03 18:36:58 +0000
  • 1f377f0d3a
    feat(API-nodes): move Rodin3D nodes to new client; removed old api client.py bigcat88 2025-11-03 17:42:01 +0200
  • 25063f25cc Merge remote-tracking branch 'upstream/master' into multitalk kijai 2025-11-03 17:41:31 +0200
  • c88ed9cfcd chore: update embedded docs to v0.3.1 ComfyUI Wiki 2025-11-03 19:34:26 +0800
  • 0f6f3c93fd format vivienfanghua 2025-11-03 09:25:04 +0000
  • 634b284407
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-03 12:00:33 +0300
  • 4e2110c794
    feat(Pika-API-nodes): use new API client (#10608) Alexander Piskun 2025-11-03 10:29:08 +0200
  • e617cddf24
    convert nodes_openai.py to V3 schema (#10604) Alexander Piskun 2025-11-03 10:28:13 +0200
  • 1f3f7a2823
    convert nodes_hypernetwork.py to V3 schema (#10583) Alexander Piskun 2025-11-03 10:21:47 +0200
  • 88df172790
    fix(caching): treat bytes as hashable (#10567) EverNebula 2025-11-03 16:16:40 +0800
  • 6d6a18b0b7
    fix(api-nodes-cloud): stop using sub-folder and absolute path for output of Rodin3D nodes (#10556) Alexander Piskun 2025-11-03 10:04:56 +0200
  • f130713953
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-03 03:07:02 +0300
  • d8b821e47b Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-11-03 07:12:55 +0900
  • 97ff9fae7e
    Clarify help text for --fast argument (#10609) comfyanonymous 2025-11-02 10:14:04 -0800
  • 6c8fdb4b2a
    Clarify help text for --fast argument comfyanonymous 2025-11-02 13:07:30 -0500
  • 15d61144e4
    feat(Pika-API-nodes): use new API client bigcat88 2025-11-02 18:43:11 +0200
  • 32b44f5d1c make training node to work with our dataset system Kohaku-Blueleaf 2025-11-03 00:33:54 +0800
  • 64da0c47c0
    fix(api-nodes-cloud): stop using sub-folder and absolute path for output of Rodin3D nodes Alexander Piskun 2025-10-30 19:51:36 +0200
  • 02064cb6e5 add argument to skip symlink scan Mohamed Oumoumad 2025-11-02 15:04:02 +0100
  • 7119b278d8 Merge branch 'master' into dataset-process-nodes Kohaku-Blueleaf 2025-11-02 21:40:01 +0800
  • 0f625a951c
    convert nodes_openai.py to V3 schema bigcat88 2025-11-02 09:04:27 +0200
  • 135fa49ec2
    Small speed improvements to --async-offload (#10593) rattus 2025-11-02 08:48:53 +1000
  • 44869ff786
    Fix issue with pinned memory. (#10597) comfyanonymous 2025-11-01 14:25:59 -0700
  • ca119c44fb returned kv cache for image generation Yousef Rafat 2025-11-01 23:06:11 +0200
  • be4190e25f
    Fix issue with pinned memory. comfyanonymous 2025-11-01 16:29:59 -0400
  • 20182a393f
    convert StabilityAI to use new API client (#10582) Alexander Piskun 2025-11-01 21:14:06 +0200
  • 5f109fe6a0
    added 12s-20s as available output durations for the LTXV API nodes (#10570) Alexander Piskun 2025-11-01 21:13:39 +0200
  • 7436674198 ops: prioritize mem transfer Rattus 2025-11-02 01:32:03 +1000
  • fcdb4a5661 ops: dont take an offload stream if you dont need one Rattus 2025-11-02 01:27:54 +1000
  • 10a17dc85d a bunch of fixes Yousef Rafat 2025-11-01 16:40:49 +0200
  • 80848f3c54 feat: Add RunPod Hub configuration and storage access test Bahadir Ciloglu 2025-11-01 17:25:26 +0300
  • cd8bb55239 Fix Docker build to exclude models from image Bahadir Ciloglu 2025-11-01 16:49:55 +0300
  • eff57ada77 Fix RunPod network storage mount and ComfyUI startup Bahadir Ciloglu 2025-11-01 16:32:35 +0300
  • a5ed5febf3 Fix all Python linting issues Bahadir Ciloglu 2025-11-01 16:26:38 +0300
  • e054031606 Fix Python linting issues and enhance RunPod network storage Bahadir Ciloglu 2025-11-01 16:24:00 +0300