Commit Graph

4664 Commits

Author SHA1 Message Date
Yousef Rafat a6e72425b0 small error fixes 2026-02-12 00:30:51 +02:00
Yousef Rafat 9b9c3c3b9f debugging 2026-02-11 20:33:59 +02:00
Yousef Rafat f9709a4ee6 dinov3 fixes + other 2026-02-11 01:27:54 +02:00
Yousef Rafat 221c5962c5 multiple fixes 2026-02-09 22:47:50 +02:00
Yousef Rafat b0b2273b4f small bug fixes 2026-02-09 00:41:01 +02:00
Yousef Rafat 1b73bd4b50 post-process node 2026-02-06 23:54:27 +02:00
Yousef Rafat d6006f62dd checkpoint 2026-02-06 20:35:33 +02:00
Yousef Rafat bc02ecfb9f model fixes 2026-02-06 19:28:49 +02:00
Yousef Rafat 57830e08f0 fixes to vae and cumesh impl. 2026-02-05 17:19:57 +02:00
Yousef Rafat 0ed8f5c925 apply rope and optimized attention 2026-02-05 02:34:08 +02:00
Yousef Rafat 2865e385e2 needed updates 2026-02-04 14:15:00 +02:00
Yousef Rafat 8d9faf28e6 structure model 2026-02-03 22:40:54 +02:00
Yousef Rafat 2b5b54ae83 model init working 2026-02-03 21:10:20 +02:00
Yousef Rafat 9a2c01d160 .. 2026-02-02 21:27:15 +02:00
Yousef Rafat 447f335e03 . 2026-02-02 21:23:19 +02:00
Yousef Rafat a15a1a92c4 updated the trellis2 nodes 2026-02-02 21:20:46 +02:00
Yousef R. Gamaleldin da84a2b868 Merge branch 'master' into trellis2 2026-02-02 18:13:58 +02:00
comfyanonymous dd86b15521
Enable embeddings for some qwen 3 models. (#12218) 2026-02-02 03:51:09 -05:00
comfyanonymous 021ba20719
Fix issue with parameters on root model object. (#12216) 2026-02-01 20:12:52 -05:00
rattus b60be02aaf
requirements: bump comfy-aimdo to 0.1.7 (#12211) 2026-02-01 20:10:15 -05:00
rattus 2b5da3b72e
dynamic_vram: silence pytorch buffer warning (#12210)
This is log clutter and concerning to users. Its a false alarm.
2026-02-01 20:09:55 -05:00
rattus 794d05bdb1
dynamic_vram: respect argument cast dtypes in non-comfy weights (#12209)
This function has a dtype argument that allows the caller to set the
dtype in the cast. TIL Some models override this on weight casts, which
means its the highest priority.

Priority scheme is: argument > model dtype > state dict dtype
2026-02-01 20:09:21 -05:00
rattus 361b9a82a3
fix pinning with model defined dtype (#12208)
pinned memory was converted back to pinning the CPU side weight without
any changes. Fix the pinner to use the CPU weight and not the model defined
geometry. This will either save RAM or stop buffer overruns when the types
mismatch.

Fix the model defined weight caster to use the [ s.weight, s.bias ]
interpretation, as xfer_dest might be the flattened pin now. Fix the detection
of needing to cast to not be conditional on !pin.
2026-02-01 08:42:32 -08:00
comfyanonymous 667a1b8878
Fix some custom nodes breaking. (#12203) 2026-02-01 01:55:18 -05:00
Christian Byrne 32621c6a11
fix: improve error message when node type is missing (#12194)
- Change error type from 'invalid_prompt' to 'missing_node_type' for frontend detection
- Add extra_info with node_id, class_type, and node_title (from _meta.title)
- Improve user-facing message: 'Node X not found. The custom node may not be installed.'
2026-02-01 01:13:48 -05:00
rattus f8acd9c402
Reduce RAM usage, fix VRAM OOMs, and fix Windows shared memory spilling with adaptive model loading (#11845) 2026-02-01 01:01:11 -05:00
comfyanonymous 873de5f37a
KV cache implementation for using llama models for text generation. (#12195) 2026-01-31 21:11:11 -05:00
Jedrzej Kosinski aa6f7a83bb
Send is_input_list on v1 and v3 schema to frontend (#12188) 2026-01-31 20:05:11 -05:00
Jedrzej Kosinski 6ea8c128a3
Assets Part 2 - add more endpoints (#12125) 2026-01-31 02:22:05 -05:00
Alexander Piskun 6e469a3f35
feat(api-nodes): add Q3 models and support for Extend and MultiFrame Vidu endpoints (#12175)
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
2026-01-30 22:44:08 -08:00
comfyanonymous b8f848bfe3
Fix model not working with any res. (#12186) 2026-01-31 00:12:48 -05:00
comfyanonymous 4064062e7d
Update python patch version in dep workflow. (#12184) 2026-01-30 20:20:06 -05:00
pythongosssss 8aabe2403e
Add color type and Color to RGB Int node (#12145)
* add color type and color to rgb int node

* review fix for allowing output

---------

Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
2026-01-30 15:01:33 -08:00
Alexander Piskun 0167653781
feat(api-nodes): add RecraftCreateStyleNode node (#12055)
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
2026-01-30 14:04:43 -08:00
Yousef R. Gamaleldin 6ea2e5b288 init 2026-01-30 23:34:48 +02:00
Jedrzej Kosinski 0a7993729c
Remove NodeInfoV3-related code; we are almost 100% guaranteed to stick with NodeInfoV1 for the foreseable future (#12147)
Co-authored-by: guill <jacob.e.segal@gmail.com>
2026-01-30 10:21:48 -08:00
comfyanonymous bbe2c13a70
Make empty hunyuan latent 1.0 work with the 1.5 model. (#12171) 2026-01-29 23:52:22 -05:00
Christian Byrne 3aace5c8dc
fix: count non-dict items in outputs_count (#12166)
Move count increment before isinstance(item, dict) check so that
non-dict output items (like text strings from PreviewAny node)
are included in outputs_count.

This aligns OSS Python with Cloud's Go implementation which uses
len(itemsArray) to count ALL items regardless of type.

Amp-Thread-ID: https://ampcode.com/threads/T-019c0bb5-14e0-744f-8808-1e57653f3ae3

Co-authored-by: Amp <amp@ampcode.com>
2026-01-29 17:10:08 -08:00
comfyanonymous b0d9708974 ComfyUI v0.11.1 2026-01-29 00:27:23 -05:00
comfyanonymous c9b633d84f
Add missing spacial downscale ratios. (#12146) 2026-01-28 20:52:51 -05:00
ComfyUI Wiki 1711020904
chore: update workflow templates to v0.8.27 (#12141) 2026-01-28 12:48:02 -05:00
Dr.Lt.Data d9b8567547
bump manager version to 4.1b1 (#12140) 2026-01-28 12:47:37 -05:00
Alexander Piskun 6c5f906bf2
feat(api-nodes): add Grok Imagine nodes (#12136) 2026-01-28 12:46:57 -05:00
comfyanonymous 4f5bd39b1c
Update Python 3.14 compatibility notes in README (#12127) 2026-01-27 19:58:48 -05:00
guill dcff27fe3f
Add support for dev-only nodes. (#12106)
When a node is declared as dev-only, it doesn't show in the default UI
unless the dev mode is enabled in the settings. The intention is to
allow nodes related to unit testing to be included in ComfyUI
distributions without confusing the average user.
2026-01-27 13:03:29 -08:00
comfyanonymous 09725967cf ComfyUI version v0.11.0 2026-01-26 23:08:01 -05:00
ComfyUI Wiki 5f62440fbb
chore: update workflow templates to v0.8.24 (#12103) 2026-01-26 22:47:33 -05:00
ComfyUI Wiki ac91c340f4
Update workflow templates to v0.8.23 (#12102) 2026-01-26 21:39:39 -05:00
comfyanonymous 2db3b0ff90
Update amd portable for rocm 7.2 (#12101)
* Update amd portable for rocm 7.2

* Update Python patch version in release workflow
2026-01-26 19:49:31 -05:00
rattus 6516ab335d
wan-vae: Switch off feature cache for single frame (#12090)
The code throughout is None safe to just skip the feature cache saving
step if none. Set it none in single frame use so qwen doesn't burn VRAM
on the unused cache.
2026-01-26 19:40:19 -05:00