Commit Graph

  • 7f8d7f2968 refactor flux/chroma process_img function to comfy.ldm.common_dit to be used as shared function. silveroxides 2025-11-14 12:03:54 +01:00
  • 6c02c6b71f
    Revise README for ComfyUI-ZLUDA updates patientx 2025-11-14 12:55:58 +03:00
  • 9f9ce655f2
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-14 12:55:30 +03:00
  • 385d102633
    Revise README for ComfyUI project patientx 2025-11-14 12:55:23 +03:00
  • 3904e8a21b
    Merge branch 'comfyanonymous:master' into feature/custom_nodes-envvar Sas van Gulik 2025-11-14 09:36:32 +01:00
  • 01e93c7b7f
    Merge branch 'master' into yousef-higgsv2 Yousef R. Gamaleldin 2025-11-14 10:28:12 +02:00
  • 443056c401
    Fix custom nodes import error. (#10747) comfyanonymous 2025-11-14 00:26:05 -08:00
  • 438c3a650c
    Fix custom nodes import error. comfyanonymous 2025-11-14 03:25:38 -05:00
  • 7b4c1e8031 async cache revamp Added an async loading and offloading of moe layers, having consistent memory with oom errors. Used to give oom error after the third layer with 24 giga bytes gpu, now goes to the end with consistent memory with minimal latency Yousef Rafat 2025-11-14 09:15:16 +02:00
  • f60923590c
    Use same code for chroma and flux blocks so that optimizations are shared. (#10746) comfyanonymous 2025-11-13 22:28:05 -08:00
  • c6414ed182 ruff. comfyanonymous 2025-11-14 01:20:34 -05:00
  • 728db5c47c Use same code for chroma and flux blocks so that optimizations are shared. comfyanonymous 2025-11-14 01:18:58 -05:00
  • 1ef328c007
    Better instructions for the portable. (#10743) comfyanonymous 2025-11-13 18:32:39 -08:00
  • 6fd7e60f05
    Update README with model file placement instructions comfyanonymous 2025-11-13 21:31:56 -05:00
  • 55e7a2cc03
    Enhance download instructions for Windows extraction comfyanonymous 2025-11-13 21:28:28 -05:00
  • 94c298f962
    flux: reduce VRAM usage (#10737) rattus 2025-11-14 10:02:03 +10:00
  • 13aa23dff4 Make sure other unfinished dynamic types are not accidentally used Jedrzej Kosinski 2025-11-13 15:49:41 -08:00
  • 2fde9597f4
    feat: add create_time dict to prompt field in /history and /queue (#10741) ric-yu 2025-11-13 15:11:52 -08:00
  • 19826f400c feat: add create_time dict to prompt field in /history and /queue Richard Yu 2025-11-13 14:50:34 -08:00
  • 66835171c6
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-14 00:02:26 +03:00
  • f91078b1ff
    add PR template for API-Nodes (#10736) Alexander Piskun 2025-11-13 20:05:26 +02:00
  • aa33e4d49d loose req Neo 2025-11-14 01:49:50 +08:00
  • e148a7f1bb mm: discard async errors from pinning failures Rattus 2025-11-13 21:38:04 +10:00
  • d2e06df2a7 flux: reduce VRAM usage Rattus 2025-11-14 01:50:36 +10:00
  • 1f130ae8b8
    add PR template for API-Nodes bigcat88 2025-11-13 15:34:57 +02:00
  • 6e3c70ac0d
    Merge branch 'comfyanonymous:master' into feature/custom_nodes-envvar Sas van Gulik 2025-11-13 12:29:52 +01:00
  • 5083c0225a
    Update README.md patientx 2025-11-13 13:23:41 +03:00
  • 184fdd1103
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-13 13:23:21 +03:00
  • bdbf42ee05
    Update README.md patientx 2025-11-13 13:23:13 +03:00
  • 59381ecbd2 Add get_dynamic function, not yet filled out correctly Jedrzej Kosinski 2025-11-12 23:24:39 -08:00
  • e3ba819d2c Initial work on DynamicCombo Jedrzej Kosinski 2025-11-12 18:46:15 -08:00
  • 33bbf75eeb Mark Switch node as Beta v3-match-type Jedrzej Kosinski 2025-11-12 17:44:42 -08:00
  • ef4179e894 Merge branch 'master' into v3-match-type Jedrzej Kosinski 2025-11-12 23:25:58 -08:00
  • 0066a50beb update frontend to 1.30 bymyself 2025-11-12 17:07:16 -08:00
  • 3b3ef9a77a
    Quantized Ops fixes (#10715) contentis 2025-11-13 00:26:52 +01:00
  • 39a5c5621e
    Merge branch 'comfyanonymous:master' into master Sam Pullara 2025-11-12 15:06:53 -08:00
  • 8b0b93df51
    Update Python 3.14 compatibility notes in README (#10730) comfyanonymous 2025-11-12 14:04:41 -08:00
  • 9747b75093
    Update README.md patientx 2025-11-13 00:55:34 +03:00
  • 00609a5102
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-13 00:55:19 +03:00
  • f1c8217364
    Update README.md patientx 2025-11-13 00:55:13 +03:00
  • 690b072635
    Fix typo in Python version description comfyanonymous 2025-11-12 16:41:17 -05:00
  • 7730b714e2
    Update Python 3.14 compatibility notes in README comfyanonymous 2025-11-12 16:40:22 -05:00
  • 1c7eaeca10
    qwen: reduce VRAM usage (#10725) rattus 2025-11-13 07:20:53 +10:00
  • 18e7d6dba5
    mm/mp: always unload re-used but modified models (#10724) rattus 2025-11-13 07:19:53 +10:00
  • e1d85e7577
    Update README.md for Intel Arc GPU installation, remove IPEX (#10729) Qiacheng Li 2025-11-12 12:21:05 -08:00
  • 8cfb812c3a
    Update README.md for Intel Arc GPU installation, remove IPEX Qiacheng Li 2025-11-12 12:03:42 -08:00
  • 6044679a3c Make sure this PR only has MatchType stuff Jedrzej Kosinski 2025-11-12 10:55:14 -08:00
  • 64f07fa534
    Merge branch 'comfyanonymous:master' into feature/custom_nodes-envvar Sas van Gulik 2025-11-12 18:27:05 +01:00
  • cce156043f update tokenizers>=0.14,<0.19 is required for a normal functioning of this module, but found tokenizers==0.13.3. Neo 2025-11-12 23:54:43 +08:00
  • 644778be49
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-12 17:55:30 +03:00
  • 09c250184d
    Update graph.py Miklos Nagy 2025-11-12 15:14:45 +01:00
  • f1d1fb78cf 支持Concurrent-8 by米强滔 Neo 2025-11-12 21:38:34 +08:00
  • bc5e2f9028 add readme lspindler 2025-11-12 14:37:32 +01:00
  • 90fbb693f6 perf: optimize dictionary merging and refactor lambda function Gizem Malçok 2025-11-12 15:35:48 +03:00
  • 65994f4ea4 qwen: reduce VRAM usage Rattus 2025-11-12 18:27:36 +10:00
  • 4584d496d8
    Merge 91fdc57b0aef8974b1dfbf7793ea6ec06ff11a23 into 119941174704081a16a4c3f303d99f2fb1e95cde Ethan Yang 2025-11-12 17:43:53 +05:30
  • c49aedbf55 mm/mp: always unload re-used but modified models Rattus 2025-11-12 21:50:07 +10:00
  • 1199411747
    Don't pin tensor if not a torch.nn.parameter.Parameter (#10718) comfyanonymous 2025-11-11 16:33:30 -08:00
  • 8eea206b19 Don't pin tensor if not a torch.nn.parameter.Parameter comfyanonymous 2025-11-11 19:28:25 -05:00
  • 097400266b
    Merge branch 'comfyanonymous:master' into feature/custom_nodes-envvar Sas van Gulik 2025-11-11 23:46:31 +01:00
  • 708ee2de73 Simplify Windows launcher and PR scope: - Remove non-upstream packages from requirements.txt - Make dependency check advisory only (no auto-install) - Remove CUDA PyTorch auto-install/update flows - Trim banner and keep minimal preflight checks - Drop non-portable create_shortcut.ps1 John Alva 2025-11-11 16:18:16 -06:00
  • ef3c64449a Remove planning and PR helper docs from PR; keep copies on branch preinstall-enhancements-docs John Alva 2025-11-11 16:09:59 -06:00
  • 9d1617bb21 Initial opencl backend with dlprim-ocl https://github.com/artyom-beilis/pytorch_dlprim Stuart Axon 2025-11-11 17:37:13 +00:00
  • 5b4c2ff924 UX: preflight banner, fast torch detection, weekly full-check, non-blocking prompts, optional updates, auto port selection and browser open John Alva 2025-11-11 11:18:02 -06:00
  • 1642459b57 offload support, bug fixes, remove mixins lspindler 2025-11-11 17:19:50 +01:00
  • 9d0107ee90 Add process_img function from comfy/ldm/flux/model.py to enable the use of ScaleROPE silveroxides 2025-11-11 16:32:31 +01:00
  • 0443944dbb Merge branch 'preinstall-enhancements' of https://github.com/John-Caldwell/ComfyUI into preinstall-enhancements John-Caldwell 2025-11-11 08:41:15 -06:00
  • d90159f58b Update ASCII art banner to display COMFY John-Caldwell 2025-11-11 08:40:53 -06:00
  • 4e14be5d8d
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-11 14:02:40 +03:00
  • 9217d54a8c Merge branch 'master' into dataset-process-nodes Kohaku-Blueleaf 2025-11-11 16:38:09 +08:00
  • 12aacb978b Fix bad id/naming Kohaku-Blueleaf 2025-11-11 16:37:27 +08:00
  • 1f852778ec Add outputs' id/name Kohaku-Blueleaf 2025-11-11 16:23:24 +08:00
  • 5818270ea3 Add screenshots directory and finalize PR for review John-Caldwell 2025-11-11 01:35:31 -06:00
  • 17a262a3cf [tripo] change paramter order liangd 2025-11-11 10:45:11 +08:00
  • cfee48d3b7 Update checklist: Feature Request issue #10705 created and referenced John-Caldwell 2025-11-10 18:09:47 -06:00
  • a6769cb56e Add issue number #10705 to PR description John-Caldwell 2025-11-10 18:08:34 -06:00
  • 04139fe528 Update submission checklist and add final summary John-Caldwell 2025-11-10 18:00:29 -06:00
  • 55b7ea2bbd Add Feature Request issue content and update PR description for compliance John-Caldwell 2025-11-10 17:59:35 -06:00
  • 2bfd78c46a Add PR submission checklist and screenshot recommendations John-Caldwell 2025-11-10 17:21:41 -06:00
  • 1a56b1dcea Add comprehensive PR description for preinstall enhancements John-Caldwell 2025-11-10 17:20:54 -06:00
  • 52d13ef3a8 Add plan document for preinstall enhancements PR John-Caldwell 2025-11-10 16:30:23 -06:00
  • 5ebcab3c7d
    Update CI workflow to remove dead macOS runner. (#10704) comfyanonymous 2025-11-10 12:35:29 -08:00
  • 19dd369bc7
    revert comfyanonymous 2025-11-10 15:33:05 -05:00
  • 75082dfbba
    revert comfyanonymous 2025-11-10 15:17:07 -05:00
  • 25a1724133
    Update CI workflow to remove dead macOS runner. comfyanonymous 2025-11-10 15:08:29 -05:00
  • aa0a025df9
    Try to disable pinned memory if wrong behavior detected. comfyanonymous 2025-11-10 14:59:07 -05:00
  • f65290f9a5 Add create_shortcut.ps1 for desktop shortcut creation John-Caldwell 2025-11-10 11:54:36 -06:00
  • 1365bbf859 Enhanced run_comfyui.bat with UTF-8 encoding, progress bars, and CUDA PyTorch auto-installation John-Caldwell 2025-11-10 11:38:17 -06:00
  • b15ef9917b Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-11-11 01:58:42 +09:00
  • 0f93e63be4 Add enhanced batch file with optional dependency checking John-Caldwell 2025-11-10 10:27:52 -06:00
  • 3662d0a2ce
    Merge branch 'comfyanonymous:master' into master patientx 2025-11-10 14:05:53 +03:00
  • 4425247ad4
    Merge branch 'comfyanonymous:master' into feature/custom_nodes-envvar Sas van Gulik 2025-11-10 08:35:09 +01:00
  • 2e843f309d wan: Implement block level prefetching Rattus 2025-11-04 08:34:28 +10:00
  • 0814c1f63f qwen: Implement transformer block prefetching Rattus 2025-11-02 02:36:40 +10:00
  • e279e1f26e ops: Implement prefetching API Rattus 2025-11-02 02:35:36 +10:00
  • 95609acef4
    feat: use matrix.to for matrix links Nya Candy 2025-11-10 12:52:38 +08:00
  • c350009236
    ops: Put weight cast on the offload stream (#10697) rattus 2025-11-10 13:52:11 +10:00
  • 2d4dd3972c Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-11-10 12:48:44 +09:00
  • a5c32e5b08 ops: Put weight cast on the offload stream Rattus 2025-11-10 13:04:09 +10:00
  • 65935d512f Increase EliGen entity limit to 8 nolan4 2025-11-09 16:10:07 -08:00