Commit Graph

  • b1467da480
    execution: fold in dependency aware caching / Fix --cache-none with loops/lazy etc (#10368) rattus128 2025-10-18 06:55:15 +1000
  • 50f6a5e10d
    Merge branch 'master' into feat/api-nodes/api-client-v2 bigcat88 2025-10-17 16:45:36 +0300
  • 49597bfa3e load remains mmap strint 2025-10-17 21:43:49 +0800
  • c9c68ed78d Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-17 22:37:13 +0900
  • 01d9369018 feat(api-nodes): implement new API client for V3 nodes Alexander Piskun 2025-10-16 23:14:55 +0300
  • 02a004264f test_execution: add --cache-none to the test suite Rattus 2025-10-17 22:08:43 +1000
  • c9e0ee71ce main: re-implement --cache-none as no cache at all Rattus 2025-10-16 21:53:57 +1000
  • 6583cc0142 debug load mem strint 2025-10-17 18:28:25 +0800
  • 5c3c6c02b2 add debug log of cpu load strint 2025-10-17 16:33:14 +0800
  • b73e0547ca Add get_subgraphs_dir to ComfyExtension and PUBLISHED_SUBGRAPH_DIRS to nodes.py Jedrzej Kosinski 2025-10-16 22:38:18 -0700
  • d8d60b5609
    Do batch_slice in EasyCache's apply_cache_diff (#10376) Jedrzej Kosinski 2025-10-16 21:39:37 -0700
  • 6626f7c5c4 Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-17 12:42:54 +0900
  • 3e316d9b04 Do batch_slice in EasyCache's apply_cache_diff Jedrzej Kosinski 2025-10-16 20:18:18 -0700
  • b1293d50ef
    workaround also works on cudnn 91200 (#10375) comfyanonymous 2025-10-16 16:59:56 -0700
  • c60dceb40a
    workaround also works on cudnn 91200 comfyanonymous 2025-10-16 19:59:37 -0400
  • 19b466160c
    Workaround for nvidia issue where VAE uses 3x more memory on torch 2.9 (#10373) comfyanonymous 2025-10-16 15:16:03 -0700
  • ed36591231 Workaround for nvidia issue where VAE uses 3x more memory on torch 2.9 comfyanonymous 2025-10-16 18:03:15 -0400
  • c9d9d47b85 Merge remote-tracking branch 'origin/feat/api-nodes/api-client-v2' into feat/api-nodes/api-client-v2 Alexander Piskun 2025-10-16 21:39:02 +0300
  • 462ce028be
    feat(api-nodes): implement new API client for V3 nodes bigcat88 2025-10-14 19:49:47 +0300
  • bc0ad9bb49
    fix(api-nodes): remove "veo2" model from Veo3 node (#10372) Alexander Piskun 2025-10-16 20:12:50 +0300
  • f16f818803
    fix(api-nodes): remove "veo2" model from Veo3 node bigcat88 2025-10-16 19:32:36 +0300
  • e5ff6a1b53 refine log strint 2025-10-16 22:47:03 +0800
  • 71b23d12e4 rm useless log strint 2025-10-16 22:34:55 +0800
  • a207301c25 rm useless log strint 2025-10-16 22:28:06 +0800
  • 9352987e9b add log strint 2025-10-16 22:25:17 +0800
  • 59c482fd77 Implement mixed precision operations with a registry design and metadate for quant spec in checkpoint. lspindler 2025-10-16 16:07:43 +0200
  • c1eac555c0 add debug log strint 2025-10-16 21:42:48 +0800
  • 2b222962c3 add debug log strint 2025-10-16 21:42:02 +0800
  • 7b0643ada1
    Merge branch 'comfyanonymous:master' into master patientx 2025-10-16 16:40:50 +0300
  • 2acd48e36d execution: fold in dependency aware caching Rattus 2025-10-16 21:30:18 +1000
  • c9762174b3 feat(api-nodes): implement new API client for V3 nodes bigcat88 2025-10-14 19:49:47 +0300
  • f40e00cb35 add detail debug strint 2025-10-16 19:38:13 +0800
  • fa19dd4620 debug offload strint 2025-10-16 17:00:47 +0800
  • 6e33ee391a debug error strint 2025-10-16 16:45:08 +0800
  • 4054b4bf38
    feat: deprecated API alert (#10366) Rizumu Ayaka 2025-10-16 16:13:31 +0800
  • 756df14759
    feat: deprecated API alert Rizumu Ayaka 2025-10-16 15:55:10 +0800
  • 55ac7d333c
    Bump frontend to 1.28.7 (#10364) Arjan Singh 2025-10-15 20:30:39 -0700
  • de2de04699
    Bump frontend to 1.28.7 Arjan Singh 2025-10-15 20:18:49 -0700
  • 0802f3a635 Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-16 12:06:19 +0900
  • 4661d1db5a Bring patches changes from _calc_cond_batch into _calc_cond_batch_multigpu worksplit-multigpu Jedrzej Kosinski 2025-10-15 17:34:36 -0700
  • b326a544d5 Merge branch 'master' into worksplit-multigpu Jedrzej Kosinski 2025-10-15 17:33:02 -0700
  • afa8a24fe1
    refactor: Replace manual patches merging with merge_nested_dicts (#10360) Faych 2025-10-16 01:16:09 +0100
  • 31b7592179 Fix missing safe initialization of descendants in loops HelloClyde 2025-10-16 07:59:40 +0800
  • 493b81e48f
    Fix order of inputs nested merge_nested_dicts (#10362) Jedrzej Kosinski 2025-10-15 16:47:26 -0700
  • 4fbf6cc387 Merge branch 'master' into fix/issue-10329 HelloClyde 2025-10-16 07:38:11 +0800
  • 1e2259dc4b Fix order of inputs nested merge_nested_dicts Jedrzej Kosinski 2025-10-15 16:23:43 -0700
  • 20c2dea6e9
    Update README.md patientx 2025-10-16 02:22:28 +0300
  • 839c8308ec
    Merge branch 'comfyanonymous:master' into master patientx 2025-10-16 02:21:42 +0300
  • 1fc0bdaa17
    Update README.md patientx 2025-10-16 02:21:36 +0300
  • 6b035bfce2
    Latest pytorch stable is cu130 (#10361) comfyanonymous 2025-10-15 15:48:12 -0700
  • ba87233fa9
    Latest stable is cu130 comfyanonymous 2025-10-15 18:47:47 -0400
  • 74b7f0b04b
    feat(api-nodes): add Veo3.1 model (#10357) Alexander Piskun 2025-10-16 01:41:45 +0300
  • f72c6616b2
    Add TemporalScoreRescaling node (#10351) chaObserv 2025-10-16 06:12:25 +0800
  • 981f26510c refactor: Replace manual patches merging with merge_nested_dicts neverbiasu 2025-10-15 23:05:45 +0100
  • 19ad129d37 Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-16 06:40:04 +0900
  • 3265d90eb1
    Merge 79c8b31a1e into 1c10b33f9b Anirudh M 2025-10-15 22:12:03 +0100
  • 6b29078837
    feat(api-nodes): add Veo3.1 model bigcat88 2025-10-15 21:08:54 +0300
  • fbf9e0063a Mention image generation in tsr_k's tooltip chaObserv 2025-10-15 22:40:38 +0800
  • efb8350cb4 Add Qwen Image resolutions doctorpangloss 2025-10-15 07:25:33 -0700
  • 490f5112cb
    Update README.md patientx 2025-10-15 12:18:33 +0300
  • 26589a3a0b
    Merge branch 'comfyanonymous:master' into master patientx 2025-10-15 12:18:21 +0300
  • 1ee189ef99
    Update README.md patientx 2025-10-15 12:18:14 +0300
  • 7a79d9add3
    Fix the issue where subgraph does not work under --cache-none mode (#10329) HelloClyde 2025-10-15 17:09:40 +0800
  • c2d073ecbf Add TemporalScoreRescaling node chaObserv 2025-10-15 11:21:43 +0800
  • 1c10b33f9b
    gfx942 doesn't support fp8 operations. (#10348) comfyanonymous 2025-10-14 21:21:11 -0700
  • c916a805aa
    gfx942 doesn't support fp8 operations. comfyanonymous 2025-10-15 00:17:20 -0400
  • db61dc3481 Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-15 12:34:12 +0900
  • c5a8ec3f67 Create nodes_dataset.py Kohaku-Blueleaf 2025-10-15 09:32:09 +0800
  • ddfce1af4f
    Bump frontend to 1.28.6 (#10345) Arjan Singh 2025-10-14 18:08:23 -0700
  • 7d493629a4
    Separate Int node without control_after_generate Silver 2025-10-15 03:06:19 +0200
  • 8c3bcb5f1f
    Bump frontend to 1.28.6 Arjan Singh 2025-10-14 16:39:56 -0700
  • 5fbc8a1b80 Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-15 06:43:20 +0900
  • 7a883849ea
    api-nodes: fixed dynamic pricing format; import comfy_io directly (#10336) Alexander Piskun 2025-10-14 09:55:56 +0300
  • 84867067ea
    Python 3.14 instructions. (#10337) comfyanonymous 2025-10-13 23:09:12 -0700
  • 54364adc19
    Python 3.14 instructions. comfyanonymous 2025-10-14 02:08:27 -0400
  • 2c591cb6d0
    api-nodes: fixed dynamic pricing format; import comfy_io directly bigcat88 2025-10-14 08:22:51 +0300
  • d89dd5f0b0 Satisfy ruff Jedrzej Kosinski 2025-10-13 22:00:34 -0700
  • 8cbbf0be6c Merge branch 'master' into worksplit-multigpu Jedrzej Kosinski 2025-10-13 21:53:14 -0700
  • 61133af772 Add '--flipflop-offload' startup argument Jedrzej Kosinski 2025-10-13 21:10:44 -0700
  • 586a8de8da Merge branch 'master' into flipflop-stream Jedrzej Kosinski 2025-10-13 21:04:37 -0700
  • 3374e900d0
    Faster workflow cancelling. (#10301) comfyanonymous 2025-10-13 20:43:53 -0700
  • 51696e3fdc ComfyUI version 0.3.65 v0.3.65 comfyanonymous 2025-10-13 23:39:55 -0400
  • b180f47d0e Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-14 12:34:58 +0900
  • dfff7e5332
    Better memory estimation for the SD/Flux VAE on AMD. (#10334) comfyanonymous 2025-10-13 19:37:19 -0700
  • d3806a21ba Better memory estimation for the SD/Flux VAE on AMD. comfyanonymous 2025-10-13 22:24:24 -0400
  • e4ea393666
    Fix loading old stable diffusion ckpt files on newer numpy. (#10333) comfyanonymous 2025-10-13 19:18:58 -0700
  • 1033e71359 Fix loading old stable diffusion ckpt files on newer numpy. comfyanonymous 2025-10-13 22:14:32 -0400
  • c8674bc6e9
    Enable RDNA4 pytorch attention on ROCm 7.0 and up. (#10332) comfyanonymous 2025-10-13 18:19:03 -0700
  • 26c1a84e89 Enable RDNA4 pytorch attention on ROCm 7.0 and up. comfyanonymous 2025-10-13 20:32:29 -0400
  • eae7a58e60
    Merge branch 'comfyanonymous:master' into master patientx 2025-10-14 02:07:30 +0300
  • 2b47f4a38e Merge branch 'master' into dr-support-pip-cm Dr.Lt.Data 2025-10-14 07:36:42 +0900
  • 3dfdcf66b6
    convert nodes_hunyuan.py to V3 schema (#10136) Alexander Piskun 2025-10-13 22:36:26 +0300
  • eeea67e598
    Merge fd20999994 into 95ca2e56c8 Kimbing Ng 2025-10-13 12:35:53 -0700
  • 95ca2e56c8
    WAN2.2: Fix cache VRAM leak on error (#10308) rattus128 2025-10-14 05:23:11 +1000
  • 27ffd12c45
    add indent=4 kwarg to json.dumps() (#10307) Daniel Harte 2025-10-13 20:14:52 +0100
  • e693e4db6a
    Always set diffusion model to eval() mode. (#10331) comfyanonymous 2025-10-13 11:57:27 -0700
  • 348636f5c4
    Always set diffusion model to eval() mode. comfyanonymous 2025-10-13 14:52:48 -0400
  • f87480188a Set Flux models to eval mode to restore FP8 performance matthew 2025-10-13 14:34:36 -0400
  • 2177439b80
    convert nodes_customer_sampler.py to V3 schema bigcat88 2025-10-04 19:01:44 +0300
  • 25f7bbed78 ruff check Yousef Rafat 2025-10-13 19:46:03 +0300