d7b4bf21a2
Auto enable mem efficient attention on gfx1100 on pytorch nightly 2.7
...
I'm not not sure which arches are supported yet. If you see improvements in
memory usage while using --use-pytorch-cross-attention on your AMD GPU let
me know and I will add it to the list.
2025-02-14 04:18:14 -05:00
042a905c37
Open yaml files with utf-8 encoding for extra_model_paths.yaml ( #6807 )
...
* Using utf-8 encoding for yaml files.
* Fix test assertion.
2025-02-13 20:39:04 -05:00
019c7029ea
Add a way to set a different compute dtype for the model at runtime.
...
Currently only works for diffusion models.
2025-02-13 20:34:03 -05:00
8773ccf74d
Better memory estimation for ROCm that support mem efficient attention.
...
There is no way to check if the card actually supports it so it assumes
that it does if you use --use-pytorch-cross-attention with yours.
2025-02-13 08:32:36 -05:00
1d5d6586f3
Fix ruff.
2025-02-12 06:49:16 -05:00
35740259de
mix_ascend_bf16_infer_err ( #6794 )
2025-02-12 06:48:11 -05:00
ab888e1e0b
Add add_weight_wrapper function to model patcher.
...
Functions can now easily be added to wrap/modify model weights.
2025-02-12 05:55:35 -05:00
d9f0fcdb0c
Cleanup.
2025-02-11 17:17:03 -05:00
b124256817
Fix for running via DirectML ( #6542 )
...
* Fix for running via DirectML
Fix DirectML empty image generation issue with Flux1. add CPU fallback for unsupported path. Verified the model works on AMD GPUs
* fix formating
* update casual mask calculation
2025-02-11 17:11:32 -05:00
af4b7c91be
Make --force-fp16 actually force the diffusion model to be fp16.
2025-02-11 08:33:09 -05:00
e57d2282d1
Fix incorrect Content-Type for WebP images ( #6752 )
2025-02-11 04:48:35 -05:00
4027466c80
Make lumina model work with any latent resolution.
2025-02-10 00:24:20 -05:00
095d867147
Remove useless function.
2025-02-09 07:02:57 -05:00
caeb27c3a5
res_multistep: Fix cfgpp and add ancestral samplers ( #6731 )
2025-02-08 19:39:58 -05:00
3d06e1c555
Make error more clear to user.
2025-02-08 18:57:24 -05:00
43a74c0de1
Allow FP16 accumulation with --fast ( #6453 )
...
Currently only applies to PyTorch nightly releases. (>=20250208)
2025-02-08 17:00:56 -05:00
af93c8d1ee
Document which text encoder to use for lumina 2.
2025-02-08 06:57:25 -05:00
832e3f5ca3
Fix another small bug in attention_bias redux ( #6737 )
...
* fix a bug in the attn_masked redux code when using weight=1.0
* oh shit wait there was another bug
2025-02-07 14:44:43 -05:00
079eccc92a
Don't compress http response by default.
...
Remove argument to disable it.
Add new --enable-compress-response-body argument to enable it.
2025-02-07 03:29:21 -05:00
b6951768c4
fix a bug in the attn_masked redux code when using weight=1.0 ( #6721 )
2025-02-06 16:51:16 -05:00
fca304debf
Update frontend to v1.8.14 ( #6724 )
...
Co-authored-by: huchenlei <20929282+huchenlei@users.noreply.github.com >
2025-02-06 10:43:10 -05:00
14880e6dba
Remove some useless code.
2025-02-06 05:00:37 -05:00
f1059b0b82
Remove unused GET /files API endpoint ( #6714 )
2025-02-05 18:48:36 -05:00
debabccb84
Bump ComfyUI version to v0.3.14
2025-02-05 15:48:13 -05:00
37cd448529
Set the shift for Lumina back to 6.
2025-02-05 14:49:52 -05:00
94f21f9301
Upcasting rope to fp32 seems to make no difference in this model.
2025-02-05 04:32:47 -05:00
60653004e5
Use regular numbers for rope in lumina model.
2025-02-05 04:17:25 -05:00
a57d635c5f
Fix lumina 2 batches.
2025-02-04 21:48:11 -05:00
016b219dcc
Add Lumina Image 2.0 to Readme.
2025-02-04 08:08:36 -05:00
8ac2dddeed
Lower the default shift of lumina to reduce artifacts.
2025-02-04 06:50:37 -05:00
3e880ac709
Fix on python 3.9
2025-02-04 04:20:56 -05:00
e5ea112a90
Support Lumina 2 model.
2025-02-04 04:16:30 -05:00
8d88bfaff9
allow searching for new .pt2 extension, which can contain AOTI compiled modules ( #6689 )
2025-02-03 17:07:35 -05:00
ed4d92b721
Model merging nodes for cosmos.
2025-02-03 03:31:39 -05:00
932ae8d9ca
Update frontend to v1.8.13 ( #6682 )
...
Co-authored-by: huchenlei <20929282+huchenlei@users.noreply.github.com >
2025-02-02 17:54:44 -05:00
44e19a28d3
Use maximum negative value instead of -inf for masks in text encoders.
...
This is probably more correct.
2025-02-02 09:46:00 -05:00
0a0df5f136
better guide message for sageattention ( #6634 )
2025-02-02 09:26:47 -05:00
24d6871e47
add disable-compres-response-body cli args; add compress middleware; ( #6672 )
2025-02-02 09:24:55 -05:00
9e1d301129
Only use stable cascade lora format with cascade model.
2025-02-01 06:35:22 -05:00
768e035868
Add node for preview 3d animation ( #6594 )
...
* Add node for preview 3d animation
* remove bg_color param
* remove animation_speed param
2025-01-31 10:09:07 -08:00
669e0497ea
Update frontend to v1.8.12 ( #6662 )
...
Co-authored-by: huchenlei <20929282+huchenlei@users.noreply.github.com >
2025-01-31 10:07:37 -08:00
541dc08547
Update Readme.
2025-01-31 08:35:48 -05:00
8d8dc9a262
Allow batch of different sigmas when noise scaling.
2025-01-30 06:49:52 -05:00
2f98c24360
Update Readme with link to instruction for Nvidia 50 series.
2025-01-30 02:12:43 -05:00
ef85058e97
Bump ComfyUI version to v0.3.13
2025-01-29 16:07:12 -05:00
f9230bd357
Update the python version in some workflows.
2025-01-29 15:54:13 -05:00
537c27cbf3
Bump default cuda version in standalone package to 126.
2025-01-29 08:13:33 -05:00
6ff2e4d550
Remove logging call added in last commit.
...
This is called before the logging is set up so it messes up some things.
2025-01-29 08:08:01 -05:00
222f48c0f2
Allow changing folder_paths.base_path via command line argument. ( #6600 )
...
* Reimpl. CLI arg directly inside folder_paths.
* Update tests to use CLI arg mocking.
* Revert last-minute refactor.
* Fix test state polution.
2025-01-29 08:06:28 -05:00
13fd4d6e45
More friendly error messages for corrupted safetensors files.
2025-01-28 09:41:09 -05:00
