Commit Graph

  • 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
  • 91494226db Configure RunPod network storage for models Bahadir Ciloglu 2025-11-01 16:13:45 +0300
  • 4f5fd5b888 Add final newline to fix last linting issue Bahadir Ciloglu 2025-11-01 16:06:28 +0300
  • 5c167f54b0 Remove unused imports and add trailing newline - fix final linting issues Bahadir Ciloglu 2025-11-01 16:04:08 +0300
  • 236a174b18 Rewrite runpod_handler.py with clean formatting - no whitespace issues Bahadir Ciloglu 2025-11-01 16:02:20 +0300
  • dc5a696d3b Fix all Python linting issues - clean whitespace and formatting Bahadir Ciloglu 2025-11-01 15:59:47 +0300
  • 2a6c31f4fb Fix Python linting issues - remove whitespace and add newline Bahadir Ciloglu 2025-11-01 15:55:35 +0300
  • 68f8909470 Simplify GitHub Actions workflow - single fast pipeline Bahadir Ciloglu 2025-11-01 15:51:41 +0300
  • 9eb154e0ea Add GitHub Actions CI/CD pipeline with RunPod integration Bahadir Ciloglu 2025-11-01 15:48:04 +0300
  • 896b98c6c1 Fix Dockerfile and handler - resolve exit code 127 error Bahadir Ciloglu 2025-11-01 15:43:21 +0300
  • 2c77183f25 Add RunPod Serverless support - Dockerfile, handler, and environment template Bahadir Ciloglu 2025-11-01 15:08:10 +0300
  • 4140263be5 Upload local ComfyUI-master files to create_image branch Bahadir Ciloglu 2025-11-01 14:44:15 +0300
  • b35cce6674
    Merge branch 'comfyanonymous:master' into master Bahadir Ciloglu 2025-11-01 14:36:58 +0300
  • a47b0ea003
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-01 14:17:11 +0300
  • f854c6b3d9
    convert StabilityAI to use new API client bigcat88 2025-10-31 15:03:14 +0200
  • c58c13b2ba
    Fix torch compile regression on fp8 ops. (#10580) comfyanonymous 2025-10-31 21:25:17 -0700
  • a58313d738
    Remove unused import from test_mixed_precision.py comfyanonymous 2025-11-01 00:18:20 -0400
  • 6f94783c00
    Remove unused import from ops.py comfyanonymous 2025-11-01 00:17:47 -0400
  • a5d6589426 Fix torch compile regression on fp8 ops. comfyanonymous 2025-11-01 00:16:22 -0400
  • d9e3ba4bec Further improvements to logic nodes, lazy evaluation and related doctorpangloss 2025-10-31 16:14:08 -0700
  • 1a25a0ad69 Merge branch 'yousef-hunyuan-image-3' of https://github.com/yousef-rafat/ComfyUI into yousef-hunyuan-image-3 Yousef Rafat 2025-10-31 23:58:22 +0200
  • 70f216bbd0 tiny bug Yousef Rafat 2025-10-31 23:58:01 +0200
  • 575fe3e92e
    Merge branch 'master' into yousef-hunyuan-image-3 Yousef R. Gamaleldin 2025-10-31 23:55:42 +0200
  • a2fff60d4c vectorized implementation of moe/fixes for issues Yousef Rafat 2025-10-31 23:53:13 +0200
  • 97f911280e Improve lazy graph evaluation, add logic operators doctorpangloss 2025-10-31 14:27:27 -0700
  • 16359abbbc Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-11-01 06:27:21 +0900
  • 0d20e44618
    Merge branch 'comfyanonymous:master' into master Sam Pullara 2025-10-31 13:41:24 -0700
  • 7f374e42c8
    ScaleROPE now works on Lumina models. (#10578) comfyanonymous 2025-10-31 12:41:40 -0700
  • b3e163b633 ScaleROPE now works on Lumina models. comfyanonymous 2025-10-31 15:29:35 -0400
  • de43880bdb Hunyuan Image 3.0 Yousef Rafat 2025-10-31 18:56:20 +0200
  • 73af6206ae
    convert nodes_hypernetwork.py to V3 schema bigcat88 2025-10-31 16:13:20 +0200
  • 15fdf84857
    added 12s-20s as available output durations for the LTXV API nodes bigcat88 2025-10-31 12:28:12 +0200
  • 3c90d0ea73
    Merge branch 'comfyanonymous:master' into master patientx 2025-10-31 12:35:51 +0300
  • c50efc7a2b fix(caching): treat bytes as hashable EverNebula 2025-10-31 16:32:50 +0800
  • e00688e134 add vivienfanghua 2025-10-31 07:40:58 +0000
  • 8f492d8f34 Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-31 12:55:36 +0900
  • 27d1bd8829
    Fix rope scaling. (#10560) comfyanonymous 2025-10-30 19:51:58 -0700
  • 7cb8b4489c Fix rope scaling. comfyanonymous 2025-10-30 22:47:31 -0400
  • 614cf9805e
    Add a ScaleROPE node. Currently only works on WAN models. (#10559) comfyanonymous 2025-10-30 19:11:38 -0700
  • 2a8610227d Add a ScaleROPE node. Currently only works on WAN models. comfyanonymous 2025-10-30 22:07:27 -0400
  • ad4b959d7e Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-31 07:31:50 +0900
  • 5f415089fc
    Merge branch 'comfyanonymous:master' into master Sam Pullara 2025-10-30 15:19:16 -0700
  • 513b0c46fb
    Add RAM Pressure cache mode (#10454) rattus 2025-10-31 07:39:02 +1000
  • b168112969
    Merge ade9a4e034 into dfac94695b Yoland Yan 2025-10-30 17:12:48 -0400
  • 6f2589f256 wip latent nodes can return None for graceful behavior in multi-reference-latent scenarios Benjamin Berman 2025-10-30 12:38:02 -0700
  • 769dcd1a04 initial checkin lanluo-nvidia 2025-10-30 12:18:50 -0700
  • dfac94695b
    fix img2img operation in Dall2 node (#10552) Alexander Piskun 2025-10-30 19:22:35 +0200
  • d2e1e91458 chore: update workflow templates to v0.2.9 ComfyUI Wiki 2025-10-31 00:29:28 +0800
  • 897ffeb5d2 Merge remote-tracking branch 'upstream/master' into multitalk kijai 2025-10-30 16:06:32 +0200
  • 14424c7a56
    fix img2img operation in Dall2 node bigcat88 2025-10-30 15:00:02 +0200
  • d2b87e674a execution: Convert the cache entry to NamedTuple Rattus 2025-10-30 20:40:53 +1000
  • 469a2b3fa0
    Merge branch 'comfyanonymous:master' into master patientx 2025-10-30 11:42:54 +0300
  • 0f84e80f2b Use single apply_rope function across models lspindler 2025-10-30 08:42:42 +0100
  • 163b629c70
    use new API client in Pixverse and Ideogram nodes (#10543) Alexander Piskun 2025-10-30 08:49:03 +0200
  • 26e0bac40c
    use new API client in Pixverse and Ideogram nodes bigcat88 2025-10-30 07:45:06 +0200
  • 91fdc57b0a
    Update README.md with OpenVINO node messages Ethan Yang 2025-10-30 10:14:10 +0800
  • 7907b8d6be
    Merge branch 'comfyanonymous:master' into master patientx 2025-10-30 03:16:55 +0300
  • 998bf60beb
    Add units/info for the numbers displayed on 'load completely' and 'load partially' log messages (#10538) Jedrzej Kosinski 2025-10-29 16:37:06 -0700
  • 906c089957
    Fix small performance regression with fp8 fast and scaled fp8. (#10537) comfyanonymous 2025-10-29 16:29:01 -0700
  • cfece0875c Add units/info for the numbers displayed on 'load completely' and 'load partially' log messages Jedrzej Kosinski 2025-10-29 16:27:44 -0700
  • 459dbb1e4b Fix small performance regression with fp8 fast and scaled fp8. comfyanonymous 2025-10-29 19:22:55 -0400
  • 0b3197fde2
    for some reason pip started installing 2.x which won't work with our torch, now set to 1.0.6 patientx 2025-10-30 01:49:38 +0300
  • 82bffb7855 Better integration with logic nodes from EasyUse Benjamin Berman 2025-10-29 15:36:35 -0700
  • b88c66bfa1 Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-30 07:30:50 +0900
  • 25de7b1bfa
    Try to fix slow load issue on low ram hardware with pinned mem. (#10536) comfyanonymous 2025-10-29 14:20:27 -0700
  • ab7ab5be23
    Fix Race condition in --async-offload that can cause corruption (#10501) rattus 2025-10-30 07:17:46 +1000
  • 577ef0acb8 Try to fix slow load issue on low ram hardware with pinned mem. comfyanonymous 2025-10-29 17:15:35 -0400
  • 6d23bfde7f add tests for saving json files formatted nicely Sam Pullara 2025-10-29 13:26:49 -0700
  • 0eff10fd21 store json files pretty printed for better source control compatibiility Sam Pullara 2025-10-29 13:17:56 -0700
  • ec4fc2a09a
    Fix case of weights not being unpinned. (#10533) comfyanonymous 2025-10-29 12:48:06 -0700
  • 1a58087ac2
    Reduce memory usage for fp8 scaled op. (#10531) comfyanonymous 2025-10-29 12:43:51 -0700
  • 3c687e6633
    Fix case of weights not being unpinned. comfyanonymous 2025-10-29 15:43:30 -0400
  • ce76d8bd27
    Reduce memory usage for fp8 scaled op. comfyanonymous 2025-10-29 15:32:24 -0400
  • f2c1e3d13d
    Merge branch 'comfyanonymous:master' into master patientx 2025-10-29 21:45:42 +0300
  • 6c14f3afac
    use new API client in Luma and Minimax nodes (#10528) Alexander Piskun 2025-10-29 20:14:56 +0200
  • 90e7674f29 moved autoregressive nodes into an extra file Yousef Rafat 2025-10-29 20:01:21 +0300
  • a4eb32a4ff inserted missing is_amd() check Christopher Anderson 2025-10-29 23:48:26 +1100
  • 2d2d625ed0 Fix unit tests (no code changes, no re-release) Benjamin Berman 2025-10-29 05:26:10 -0700
  • 6ceba8c9f8 mm: sync the last stream in the queue, not the next Rattus 2025-10-27 18:54:32 +1000
  • 432a5a9d82 controlnet: adopt new cast_bias_weight synchronization scheme Rattus 2025-10-27 18:53:19 +1000