kijai
be67e2366d
Cleanup NAF
2026-07-02 11:24:16 +03:00
kijai
29e2118717
Minor cleanup
2026-07-02 10:23:17 +03:00
Jukka Seppänen
1a6d6b9961
Merge branch 'master' into pixal3d
2026-07-02 09:38:14 +03:00
kijai
2bbf53e8fc
Linting
2026-07-01 21:21:11 +03:00
Silver
2c935de1b1
Fix Qwen3-VL tokenizer crash with custom embeddings ( #14713 )
Detect Unreviewed Merge / detect (push) Waiting to run
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Execution Tests / test (macos-latest) (push) Waiting to run
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Execution Tests / test (windows-latest) (push) Waiting to run
Test server launches without errors / test (push) Waiting to run
Unit Tests / test (macos-latest) (push) Waiting to run
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Unit Tests / test (windows-2022) (push) Waiting to run
2026-07-01 21:15:07 +03:00
kijai
f3c8db510f
Refactor NAF model usage
2026-07-01 01:36:14 +03:00
kijai
eec0692bcb
Cleanup model code
2026-07-01 00:25:01 +03:00
Matt Miller
1c59659a2f
feat: make asset hashing opt-in via --enable-asset-hashing, off by default ( #14663 )
...
Add a --enable-asset-hashing CLI flag (action=store_true, default False)
and plumb it into the two asset-seeder call sites in main.py that
previously hardcoded compute_hashes=True (the startup scan and the
post-job output enqueue). Local runs now skip blake3 hashing unless the
user opts in, avoiding the startup/per-output cost on large models
directories while keeping hashing available for asset-portability
features.
Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>
2026-06-30 14:13:20 -07:00
kijai
3aae4bf741
Optimize NAF memory use
2026-06-30 21:47:43 +03:00
kijai
f4b2173cf2
Simplify model detection
2026-06-30 20:15:46 +03:00
kijai
7e39dea988
Merge remote-tracking branch 'upstream/master' into pixal3d
2026-06-30 18:13:01 +03:00
comfyanonymous
79c555ce6b
Fix int8 mm being skipped on offloaded lora weights. ( #14669 )
2026-06-28 23:52:36 -04:00
kijai
022503dbc9
Merge remote-tracking branch 'origin/master' into pixal3d
2026-06-27 18:50:04 +03:00
comfyanonymous
470ac36a0a
Fix int8 loras causing lower quality requant with wrong settings. ( #14650 )
...
* Update comfy-kitchen
* Support requantizing with same settings as orig quant.
2026-06-26 16:41:29 -07:00
kijai
36e8f62dd4
Cleanup VAE code some
2026-06-27 00:43:32 +03:00
kijai
1f7acd9354
Optimize VAE
2026-06-27 00:06:19 +03:00
kijai
a227b5529c
Remove preview
2026-06-27 00:06:03 +03:00
kijai
288f3cf134
Cleanup
2026-06-27 00:05:45 +03:00
kijai
7bd1fa6e78
Merge remote-tracking branch 'origin/master' into pixal3d
2026-06-26 16:38:24 +03:00
comfyanonymous
1a510f0423
Support int8 models. ( #14636 )
2026-06-25 11:23:58 -07:00
comfyanonymous
b910f4fa2a
More accurate memory usage factor for krea 2. ( #14594 )
2026-06-23 16:50:48 +08:00
Jukka Seppänen
2a61015582
feat: Support Krea2 ( #14589 )
Detect Unreviewed Merge / detect (push) Waiting to run
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Execution Tests / test (macos-latest) (push) Waiting to run
Execution Tests / test (windows-latest) (push) Waiting to run
Test server launches without errors / test (push) Waiting to run
Unit Tests / test (macos-latest) (push) Waiting to run
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Unit Tests / test (windows-2022) (push) Waiting to run
2026-06-22 14:35:00 -07:00
comfyanonymous
e00b55631a
Small anima optimization. ( #14557 )
2026-06-20 08:05:28 +08:00
Barish Ozbay
cd77c551d6
feat: Context Windows sampling with LTX2 models and IC-LoRa guides (CORE-3) ( #13325 )
2026-06-20 07:47:31 +08:00
comfyanonymous
52257bb435
Add negative prompt to boogu edit node and set min images to 0. ( #14529 )
2026-06-17 15:42:29 -07:00
Jukka Seppänen
e25c391888
feat: Support Boogu-Image (CORE-308) ( #14523 )
Unit Tests / test (windows-2022) (push) Waiting to run
Detect Unreviewed Merge / detect (push) Waiting to run
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Execution Tests / test (macos-latest) (push) Waiting to run
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Execution Tests / test (windows-latest) (push) Waiting to run
Test server launches without errors / test (push) Waiting to run
Unit Tests / test (macos-latest) (push) Waiting to run
Unit Tests / test (ubuntu-latest) (push) Waiting to run
2026-06-17 14:22:36 -07:00
Jukka Seppänen
ca3dbe206c
Allow using Qwen3-VL as flux2 klein text encoder (again) ( #14526 )
2026-06-17 08:45:06 -07:00
Jukka Seppänen
a590d60bb1
feat: SCAIL-2 multireference (CORE-310) ( #14509 )
...
Detect Unreviewed Merge / detect (push) Waiting to run
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Execution Tests / test (macos-latest) (push) Waiting to run
Execution Tests / test (windows-latest) (push) Waiting to run
Test server launches without errors / test (push) Waiting to run
Unit Tests / test (macos-latest) (push) Waiting to run
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Unit Tests / test (windows-2022) (push) Waiting to run
* SCAIl-2: support multiref
2026-06-17 16:21:23 +03:00
Jukka Seppänen
fc964047e7
feat: Support text generation with Qwen3-VL (CORE-276) ( #14298 )
2026-06-17 08:12:44 +08:00
kijai
805e7d5ae3
Fix TRELLIS2 texture sampling preview orientation
2026-06-17 02:27:44 +03:00
kijai
72ff035fe0
Merge remote-tracking branch 'origin/master' into pixal3d
2026-06-16 11:49:36 +03:00
rattus
ec4dec93d2
Comfy Aimdo 0.4.10 + Dynamic --reserve-vram + --vram-headroom ( #14480 )
...
* main: implement --vram-headroom
Implement --vram-headroom for dynamic vram as a hybrid debug/diagnostic
option that can be used for people who still report shared VRAM spills.
They can trial and error the setting to maintain a bit more headroom to
avoid shared VRAM spills.
* main: implement --reserve-vram
Implement --reserve-vram as extra headroom on the simple method which
is semantically as close as possible to the stated functionality and
formet behaviour of non-dynamic VRAM.
2026-06-15 07:54:36 -07:00
comfyanonymous
7277d99d3a
Use comfy kitchen apply rope in omnigen2 model. ( #14442 )
2026-06-13 09:38:39 +08:00
rattus
d7a552720c
add --high-ram option ( #14437 )
...
Add this option for users who know they have so much ram they want
to pin everything or have a pagefile that outruns their disk speed.
The removes the RAM pressure caps completely and pins behind the
primary model load forcing all models to be permanently comitted
to RAM.
2026-06-12 07:53:33 -07:00
comfyanonymous
02656ea0bb
Fix potential dtype issue with ideogram 4. ( #14436 )
2026-06-12 07:51:12 -07:00
Jedrzej Kosinski
befc321438
Make --enable-manager-legacy-ui imply --enable-manager ( #14421 )
2026-06-12 06:45:22 +08:00
Barish Ozbay
91187c58d9
Improve context window resizing for SCAIL2 (CORE-286) ( #14394 )
2026-06-11 13:37:43 +08:00
rattus
bda19b2604
ops: tolerate already force casted dynamic weight ( #14410 )
...
Some custom nodes .to weights completely out of load context which
can wreak havoc if its for a model that is not active. Detect this
condition and just let it fall-through to the non-dynamic loader
straight up.
2026-06-10 20:32:57 -07:00
rattus
6d18f4adac
main: force cudnn.benchmark to false ( #14390 )
...
Some custom nodes try to set this true globally. It messes with dynamic
VRAM with one-off spikes that can OOM but this is also very high risk
for windows where such allocations might get serviced by shared memory
fallback.
Trump it.
2026-06-10 13:54:32 -04:00
kijai
35065d500a
Fix DINOv3 ViT-H detection shadowed by generic dino3_large check
...
The dino3_large discriminator (layer.9.attention.o_proj.bias) also matches
ViT-H checkpoints since o_proj always has bias=True, so it must be checked
after the specific ViT-H (gated MLP + 32-layer) signature.
2026-06-10 10:47:30 +03:00
kijai
3af63b8961
Merge remote-tracking branch 'origin/master' into pixal3d
...
# Conflicts:
# comfy/clip_vision.py
# comfy/image_encoders/dino3.py
# comfy/supported_models.py
# comfy_extras/nodes_save_3d.py
2026-06-10 10:37:19 +03:00
kijai
a4c8b5064b
preview
2026-06-10 10:29:53 +03:00
Kohaku-Blueleaf
f350acdf21
[Trainer/bug] Ensure model is not inference mode (CORE-72) ( #13400 )
...
* Ensure model is not inference mode
* force clone inside training mode to avoid inference tensor
* Allow force deepcopy for model patcher
2026-06-09 23:07:47 -04:00
Talmaj
5ece24e73c
Depth anything 3 (Core-135) ( #13853 )
...
Co-authored-by: Alexis Rolland <alexisrolland@hotmail.com>
2026-06-10 09:28:24 +08:00
Jukka Seppänen
f8e51b674c
feat: Add Bernini-R model support (Wan video) (CORE-279) ( #14216 )
Detect Unreviewed Merge / detect (push) Waiting to run
Python Linting / Run Ruff (push) Waiting to run
Python Linting / Run Pylint (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.10, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.11, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-stable (12.1, , linux, 3.12, [self-hosted Linux], stable) (push) Waiting to run
Full Comfy CI Workflow Runs / test-unix-nightly (12.1, , linux, 3.11, [self-hosted Linux], nightly) (push) Waiting to run
Execution Tests / test (macos-latest) (push) Waiting to run
Execution Tests / test (ubuntu-latest) (push) Waiting to run
Execution Tests / test (windows-latest) (push) Waiting to run
Test server launches without errors / test (push) Waiting to run
Unit Tests / test (macos-latest) (push) Waiting to run
Unit Tests / test (ubuntu-latest) (push) Waiting to run
Unit Tests / test (windows-2022) (push) Waiting to run
2026-06-10 07:47:34 +08:00
rattus
6f01b244a2
mm: dont reset cast buffers in cleanup_models_gc() ( #14372 )
...
cleanup_models_gc can be called once per load_models_gpu via
free_memory, which in turn can de-activate an active model via
this reset_cast_buffers.
cleanup_models_gc() could also come via obscure garbage collector
paths so limit reset_cast_buffers to the post-node callsite instead.
2026-06-09 13:57:04 -04:00
Jukka Seppänen
184009c2f6
feat: Add model support for SCAIL-2 ( #14373 )
...
* initial SCAIL2 support
2026-06-09 18:24:09 +03:00
kelseyee
07c53f8f0f
Add LoRA key mapping for LTXV/LTXAV models ( #14349 )
2026-06-09 09:57:58 -04:00
rattus
1639dc7a70
main/server: Add --debug-hang ( #14371 )
...
Add an option to debug a hang with ctrl-C, dumping the backtraces to
see where its stuck or slow.
2026-06-09 09:55:00 -04:00
Jukka Seppänen
8ed7f458d0
Allow custom templates with Ideogram4 TE ( #14374 )
2026-06-09 21:11:05 +08:00
