65cfcf5b1b
New Year ruff cleanup. ( #11595 )
2026-01-01 22:06:14 -05:00
1bdc9a947f
Remove duplicate import of model_management ( #11587 )
2025-12-31 19:29:55 -05:00
d622a61874
Refactor: move clip_preprocess to comfy.clip_model ( #11586 )
2025-12-31 17:38:36 -05:00
0357ed7ec4
Add support for sage attention 3 in comfyui, enable via new cli arg ( #11026 )
...
* Add support for sage attention 3 in comfyui, enable via new cli arg
--use-sage-attiention3
* Fix some bugs found in PR review. The N dimension at which Sage
Attention 3 takes effect is reduced to 1024 (although the improvement is
not significant at this scale).
* Remove the Sage Attention3 switch, but retain the attention function
registration.
* Fix a ruff check issue in attention.py
2025-12-30 22:53:52 -05:00
178bdc5e14
Add handling for vace_context in context windows ( #11386 )
...
Co-authored-by: ozbayb <17261091+ozbayb@users.noreply.github.com>
2025-12-30 14:40:42 -08:00
0e6221cc79
Add some warnings for pin and unpin errors. ( #11561 )
2025-12-29 18:26:42 -05:00
9ca7e143af
mm: discard async errors from pinning failures ( #10738 )
...
Pretty much every error cudaHostRegister can throw also queues the same
error on the async GPU queue. This was fixed for repinning error case,
but there is the bad mmap and just enomem cases that are harder to
detect.
Do some dummy GPU work to clean the error state.
2025-12-29 18:19:34 -05:00
8fd07170f1
Comment out unused norm_final in lumina/z image model. ( #11545 )
2025-12-28 22:07:25 -05:00
2943093a53
Enable async offload by default for AMD. ( #11534 )
2025-12-27 18:54:15 -05:00
1e4e342f54
Fix noise with ancestral samplers when inferencing on cpu. ( #11528 )
2025-12-26 22:03:01 -05:00
fb478f679a
Only apply gemma quant config to gemma model for newbie. ( #11436 )
2025-12-20 01:02:43 -05:00
4c432c11ed
Implement Jina CLIP v2 and NewBie dual CLIP ( #11415 )
...
* Implement Jina CLIP v2
* Support quantized Gemma in NewBie dual CLIP
2025-12-20 00:57:22 -05:00
31e961736a
Fix issue with batches and newbie. ( #11435 )
2025-12-20 00:23:51 -05:00
3ab9748903
Disable prompt weights on newbie te. ( #11434 )
2025-12-20 00:19:47 -05:00
0aa7fa464e
Implement sliding attention in Gemma3 ( #11409 )
2025-12-20 00:16:46 -05:00
514c24d756
Fix error from logging line ( #11423 )
...
Co-authored-by: ozbayb <17261091+ozbayb@users.noreply.github.com>
2025-12-19 20:22:45 -08:00
809ce68749
Support nested tensor denoise masks. ( #11431 )
2025-12-19 19:59:25 -05:00
cc4ddba1b6
Allow enabling use of MIOpen by setting COMFYUI_ENABLE_MIOPEN=1 as an env var ( #11366 )
2025-12-19 17:01:50 -05:00
28eaab608b
Diffusion model part of Qwen Image Layered. ( #11408 )
...
Only thing missing after this is some nodes to make using it easier.
2025-12-18 20:21:14 -05:00
6a2678ac65
Trim/pad channels in VAE code. ( #11406 )
2025-12-18 18:22:38 -05:00
e4fb3a3572
Support loading Wan/Qwen VAEs with different in/out channels. ( #11405 )
2025-12-18 17:45:33 -05:00
bf7dc63bd6
skip_load_model -> force_full_load ( #11390 )
...
This should be a bit more clear and less prone to potential breakage if the
logic of the load models changes a bit.
2025-12-17 23:29:32 -05:00
86dbb89fc9
Resolution bucketing and Trainer implementation refactoring ( #11117 )
2025-12-17 22:15:27 -05:00
5d9ad0c6bf
Fix the last step with non-zero sigma in sa_solver ( #11380 )
2025-12-17 13:57:40 -05:00
827bb1512b
Add exp_heun_2_x0 sampler series ( #11360 )
2025-12-16 23:35:43 -05:00
ffdd53b327
Check state dict key to auto enable the index_timestep_zero ref method. ( #11362 )
2025-12-16 17:03:17 -05:00
bc606d7d64
Add a way to set the default ref method in the qwen image code. ( #11349 )
2025-12-16 01:26:55 -05:00
683569de55
Only enable fp16 on ZImage on newer pytorch. ( #11344 )
2025-12-15 22:33:27 -05:00
ea2c117bc3
[BlockInfo] Wan ( #10845 )
...
* block info
* animate
* tensor
* device
* revert
2025-12-15 17:59:16 -08:00
fc4af86068
[BlockInfo] Lumina ( #11227 )
...
* block info
* device
* Make tensor int again
---------
Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
2025-12-15 17:57:28 -08:00
70541d4e77
Support the new qwen edit 2511 reference method. ( #11340 )
...
index_timestep_zero can be selected in the
FluxKontextMultiReferenceLatentMethod now with the display name set to the
more generic "Edit Model Reference Method" node.
2025-12-15 19:20:34 -05:00
77b2f7c228
Add context windows callback for custom cond handling ( #11208 )
...
Co-authored-by: ozbayb <17261091+ozbayb@users.noreply.github.com>
2025-12-15 16:06:32 -08:00
dbd330454a
feat(preview): add per-queue live preview method override ( #11261 )
...
- Add set_preview_method() to override live preview method per queue item
- Read extra_data.preview_method from /prompt request
- Support values: taesd, latent2rgb, none, auto, default
- "default" or unset uses server's CLI --preview-method setting
- Add 44 tests (37 unit + 7 E2E)
2025-12-15 15:57:39 -08:00
5ac3b26a7d
Update warning for old pytorch version. ( #11319 )
...
Versions below 2.4 are no longer supported. We will not break support on purpose but will not fix it if we do.
2025-12-14 04:02:50 -05:00
6592bffc60
seeds_2: add phi_2 variant and sampler node ( #11309 )
...
* Add phi_2 solver type to seeds_2
* Add sampler node of seeds_2
2025-12-14 00:03:29 -05:00
971cefe7d4
Fix pytorch warnings. ( #11314 )
2025-12-13 18:45:23 -05:00
da2bfb5b0a
Basic implementation of z image fun control union 2.0 ( #11304 )
...
The inpaint part is currently missing and will be implemented later.
I think they messed up this model pretty bad. They added some
control_noise_refiner blocks but don't actually use them. There is a typo
in their code so instead of doing control_noise_refiner -> control_layers
it runs the whole control_layers twice.
Unfortunately they trained with this typo so the model works but is kind
of slow and would probably perform a lot better if they corrected their
code and trained it again.
2025-12-13 01:39:11 -05:00
c5a47a1692
Fix bias dtype issue in mixed ops. ( #11293 )
2025-12-12 11:49:35 -05:00
5495589db3
Respect the dtype the op was initialized in for non quant mixed op. ( #11282 )
2025-12-11 23:32:27 -05:00
eeb020b9b7
Better chroma radiance and other models vram estimation. ( #11278 )
2025-12-11 17:33:09 -05:00
ae65433a60
This only works on radiance. ( #11277 )
2025-12-11 17:15:00 -05:00
fdebe18296
Fix regular chroma radiance ( #11276 )
2025-12-11 17:09:35 -05:00
f8321eb57b
Adjust memory usage factor. ( #11257 )
2025-12-11 01:30:31 -05:00
e711aaf1a7
Lower VAE loading requirements：Create a new branch for GPU memory calculations in qwen-image vae ( #11199 )
2025-12-10 22:02:26 -05:00
17c92a9f28
Tweak Z Image memory estimation. ( #11254 )
2025-12-10 19:59:48 -05:00
791e30ff50
Fix nan issue when quantizing fp16 tensor. ( #11213 )
2025-12-09 17:03:21 -05:00
e2a800e7ef
Fix for HunyuanVideo1.5 meanflow distil ( #11212 )
2025-12-09 16:59:16 -05:00
9d252f3b70
ops: delete dead code ( #11204 )
...
This became dead code in https://github.com/comfyanonymous/ComfyUI/pull/11069
2025-12-09 00:55:13 -05:00
b9fb542703
add chroma-radiance-x0 mode ( #11197 )
2025-12-08 23:33:29 -05:00
e136b6dbb0
dequantization offload accounting (fixes Flux2 OOMs - incl TEs) ( #11171 )
...
* make setattr safe for non existent attributes
Handle the case where the attribute doesnt exist by returning a static
sentinel (distinct from None). If the sentinel is passed in as the set
value, del the attr.
* Account for dequantization and type-casts in offload costs
When measuring the cost of offload, identify weights that need a type
change or dequantization and add the size of the conversion result
to the offload cost.
This is mutually exclusive with lowvram patches which already has
a large conservative estimate and wont overlap the dequant cost so\
dont double count.
* Set the compute type on CLIP MPs
So that the loader can know the size of weights for dequant accounting.
2025-12-08 23:21:31 -05:00
comfyanonymous
mengqin
drozbay
rattus
woctordho
BradPepersAMD
Kohaku-Blueleaf
chaObserv
Haoming
Dr.Lt.Data
Farshore
Jukka Seppänen
Lodestone