Jukka Seppänen
0b5852ed5d
Support loading and using SkyReels-V1-Hunyuan-I2V ( #6862 )
...
* Support SkyReels-V1-Hunyuan-I2V
* VAE scaling
* Fix T2V
oops
* Proper latent scaling
2025-02-18 17:06:54 -05:00
comfyanonymous
aa50906886
Fix typo.
...
Let me know if this slows things down on 2000 series and below.
2025-02-18 07:28:33 -05:00
comfyanonymous
4e37ad25fd
Improve AMD arch detection.
2025-02-17 04:53:40 -05:00
comfyanonymous
4f1809faf8
bf16 manual cast works on old AMD.
2025-02-17 04:42:40 -05:00
comfyanonymous
e9c105523f
Refactor torch version checks to be more future proof.
2025-02-17 04:36:45 -05:00
Zhong-Yu Li
98f4a48979
support system prompt and cfg renorm in Lumina2 ( #6795 )
...
* support system prompt and cfg renorm in Lumina2
* fix issues with the ruff style check
2025-02-16 18:15:43 -05:00
Comfy Org PR Bot
94e80be3d0
Update frontend to v1.9.18 ( #6828 )
...
Co-authored-by: huchenlei <20929282+huchenlei@users.noreply.github.com>
2025-02-16 11:45:47 -05:00
comfyanonymous
b02aa6ea50
Disable bf16 on AMD GPUs that don't support it.
2025-02-16 05:46:10 -05:00
Terry Jia
b90c8321f5
remove light_intensity and fov from load3d ( #6742 )
2025-02-15 15:34:36 -05:00
Comfy Org PR Bot
9235e4f0cd
Update frontend to v1.9.17 ( #6814 )
...
Co-authored-by: huchenlei <20929282+huchenlei@users.noreply.github.com>
2025-02-15 04:32:47 -05:00
comfyanonymous
12c68c1fd5
Add a node to set the model compute dtype for debugging.
2025-02-15 04:15:37 -05:00
comfyanonymous
539bc3e2e0
Disable pytorch attention in VAE for AMD.
2025-02-14 05:42:14 -05:00
comfyanonymous
98c0df4724
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
Robin Huang
d0484681a3
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
comfyanonymous
451a692a3d
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
comfyanonymous
1f657be9a7
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
comfyanonymous
66d579cd19
Fix ruff.
2025-02-12 06:49:16 -05:00
zhoufan2956
0f7eb12d62
mix_ascend_bf16_infer_err ( #6794 )
2025-02-12 06:48:11 -05:00
comfyanonymous
16bd3b8441
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
comfyanonymous
2a521a2e33
Cleanup.
2025-02-11 17:17:03 -05:00
HishamC
f49d8d3d1e
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
comfyanonymous
a7e5e662ab
Make --force-fp16 actually force the diffusion model to be fp16.
2025-02-11 08:33:09 -05:00
bananasss00
cf1e84b9a4
Fix incorrect Content-Type for WebP images ( #6752 )
2025-02-11 04:48:35 -05:00
comfyanonymous
6e2027a69b
Make lumina model work with any latent resolution.
2025-02-10 00:24:20 -05:00
comfyanonymous
c80b2a425c
Remove useless function.
2025-02-09 07:02:57 -05:00
Pam
a1cd544ace
res_multistep: Fix cfgpp and add ancestral samplers ( #6731 )
2025-02-08 19:39:58 -05:00
comfyanonymous
84a5e51448
Make error more clear to user.
2025-02-08 18:57:24 -05:00
catboxanon
ca2a621e0b
Allow FP16 accumulation with --fast ( #6453 )
...
Currently only applies to PyTorch nightly releases. (>=20250208)
2025-02-08 17:00:56 -05:00
comfyanonymous
61d7b7ebb9
Document which text encoder to use for lumina 2.
2025-02-08 06:57:25 -05:00
Raphael Walker
ba163f4e34
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
comfyanonymous
6865c73a03
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
Raphael Walker
d76c0e4615
fix a bug in the attn_masked redux code when using weight=1.0 ( #6721 )
2025-02-06 16:51:16 -05:00
Comfy Org PR Bot
4e99a4ae72
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
comfyanonymous
1908648a5b
Remove some useless code.
2025-02-06 05:00:37 -05:00
Chenlei Hu
634c43686d
Remove unused GET /files API endpoint ( #6714 )
2025-02-05 18:48:36 -05:00
comfyanonymous
5c2c81e2e7
Bump ComfyUI version to v0.3.14
2025-02-05 15:48:13 -05:00
comfyanonymous
50a778e1ce
Set the shift for Lumina back to 6.
2025-02-05 14:49:52 -05:00
comfyanonymous
ff7449847e
Upcasting rope to fp32 seems to make no difference in this model.
2025-02-05 04:32:47 -05:00
comfyanonymous
f210ee69df
Use regular numbers for rope in lumina model.
2025-02-05 04:17:25 -05:00
comfyanonymous
eaf581f1ed
Fix lumina 2 batches.
2025-02-04 21:48:11 -05:00
comfyanonymous
913648db65
Add Lumina Image 2.0 to Readme.
2025-02-04 08:08:36 -05:00
comfyanonymous
0467641f12
Lower the default shift of lumina to reduce artifacts.
2025-02-04 06:50:37 -05:00
comfyanonymous
24b0e00898
Fix on python 3.9
2025-02-04 04:20:56 -05:00
comfyanonymous
e03a640306
Support Lumina 2 model.
2025-02-04 04:16:30 -05:00
Raphael Walker
bfdbecdd68
allow searching for new .pt2 extension, which can contain AOTI compiled modules ( #6689 )
2025-02-03 17:07:35 -05:00
comfyanonymous
7f08929c3e
Model merging nodes for cosmos.
2025-02-03 03:31:39 -05:00
Comfy Org PR Bot
27272fffd6
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
comfyanonymous
fc1a24c402
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
Dr.Lt.Data
4a3500c3ef
better guide message for sageattention ( #6634 )
2025-02-02 09:26:47 -05:00
KarryCharon
e12555bdbf
add disable-compres-response-body cli args; add compress middleware; ( #6672 )
2025-02-02 09:24:55 -05:00
