comfyanonymous
530412cb9d
Refactor torch version checks to be more future proof.
2025-02-17 04:36:45 -05:00
comfyanonymous
e2919d38b4
Disable bf16 on AMD GPUs that don't support it.
2025-02-16 05:46:10 -05:00
comfyanonymous
2e21122aab
Add a node to set the model compute dtype for debugging.
2025-02-15 04:15:37 -05:00
comfyanonymous
1cd6cd6080
Disable pytorch attention in VAE for AMD.
2025-02-14 05:42:14 -05:00
comfyanonymous
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
comfyanonymous
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
comfyanonymous
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
comfyanonymous
1d5d6586f3
Fix ruff.
2025-02-12 06:49:16 -05:00
comfyanonymous
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
comfyanonymous
d9f0fcdb0c
Cleanup.
2025-02-11 17:17:03 -05:00
comfyanonymous
af4b7c91be
Make --force-fp16 actually force the diffusion model to be fp16.
2025-02-11 08:33:09 -05:00
comfyanonymous
4027466c80
Make lumina model work with any latent resolution.
2025-02-10 00:24:20 -05:00
comfyanonymous
095d867147
Remove useless function.
2025-02-09 07:02:57 -05:00
comfyanonymous
3d06e1c555
Make error more clear to user.
2025-02-08 18:57:24 -05:00
comfyanonymous
af93c8d1ee
Document which text encoder to use for lumina 2.
2025-02-08 06:57:25 -05:00
comfyanonymous
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
comfyanonymous
14880e6dba
Remove some useless code.
2025-02-06 05:00:37 -05:00
comfyanonymous
debabccb84
Bump ComfyUI version to v0.3.14
2025-02-05 15:48:13 -05:00
comfyanonymous
37cd448529
Set the shift for Lumina back to 6.
2025-02-05 14:49:52 -05:00
comfyanonymous
94f21f9301
Upcasting rope to fp32 seems to make no difference in this model.
2025-02-05 04:32:47 -05:00
comfyanonymous
60653004e5
Use regular numbers for rope in lumina model.
2025-02-05 04:17:25 -05:00
comfyanonymous
a57d635c5f
Fix lumina 2 batches.
2025-02-04 21:48:11 -05:00
comfyanonymous
016b219dcc
Add Lumina Image 2.0 to Readme.
2025-02-04 08:08:36 -05:00
comfyanonymous
8ac2dddeed
Lower the default shift of lumina to reduce artifacts.
2025-02-04 06:50:37 -05:00
comfyanonymous
3e880ac709
Fix on python 3.9
2025-02-04 04:20:56 -05:00
comfyanonymous
e5ea112a90
Support Lumina 2 model.
2025-02-04 04:16:30 -05:00
comfyanonymous
ed4d92b721
Model merging nodes for cosmos.
2025-02-03 03:31:39 -05:00
comfyanonymous
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
comfyanonymous
9e1d301129
Only use stable cascade lora format with cascade model.
2025-02-01 06:35:22 -05:00
comfyanonymous
541dc08547
Update Readme.
2025-01-31 08:35:48 -05:00
comfyanonymous
8d8dc9a262
Allow batch of different sigmas when noise scaling.
2025-01-30 06:49:52 -05:00
comfyanonymous
2f98c24360
Update Readme with link to instruction for Nvidia 50 series.
2025-01-30 02:12:43 -05:00
comfyanonymous
ef85058e97
Bump ComfyUI version to v0.3.13
2025-01-29 16:07:12 -05:00
comfyanonymous
f9230bd357
Update the python version in some workflows.
2025-01-29 15:54:13 -05:00
comfyanonymous
537c27cbf3
Bump default cuda version in standalone package to 126.
2025-01-29 08:13:33 -05:00
comfyanonymous
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
comfyanonymous
13fd4d6e45
More friendly error messages for corrupted safetensors files.
2025-01-28 09:41:09 -05:00
comfyanonymous
255edf2246
Lower minimum ratio of loaded weights on Nvidia.
2025-01-27 05:26:51 -05:00
comfyanonymous
4f011b9a00
Better CLIPTextEncode error when clip input is None.
2025-01-26 06:04:57 -05:00
comfyanonymous
67feb05299
Remove redundant code.
2025-01-25 19:04:53 -05:00
comfyanonymous
6d21740346
Print ComfyUI version.
2025-01-25 15:03:57 -05:00
comfyanonymous
7fbf4b72fe
Update nightly pytorch ROCm command in Readme.
2025-01-24 06:15:54 -05:00
comfyanonymous
14ca5f5a10
Remove useless code.
2025-01-24 06:15:54 -05:00
comfyanonymous
96e2a45193
Remove useless code.
2025-01-23 05:56:23 -05:00
comfyanonymous
d6bbe8c40f
Remove support for python 3.8.
2025-01-22 17:04:30 -05:00
comfyanonymous
a7fe0a94de
Refactor and fixes for video latents.
2025-01-22 06:37:46 -05:00
comfyanonymous
d303cb5341
Add missing case to CLIPLoader.
2025-01-21 08:57:04 -05:00
comfyanonymous
fb2ad645a3
Add FluxDisableGuidance node to disable using the guidance embed.
2025-01-20 14:50:24 -05:00
comfyanonymous
d8a7a32779
Cleanup old TODO.
2025-01-20 03:44:13 -05:00
comfyanonymous
a00e1489d2
LatentBatch fix for video latents
2025-01-19 06:02:14 -05:00
comfyanonymous
507199d9a8
Uni pc sampler now works with audio and video models.
2025-01-18 05:27:58 -05:00
comfyanonymous
2f3ab40b62
Add warning when using old pytorch versions.
2025-01-17 18:47:27 -05:00
comfyanonymous
7fc3ccdcc2
Add that nvidia cosmos is supported to the README.
2025-01-16 21:17:18 -05:00
comfyanonymous
55add50220
Bump ComfyUI version to v0.3.12
2025-01-16 18:11:57 -05:00
comfyanonymous
0aa2368e46
Fix some cosmos fp8 issues.
2025-01-16 17:45:37 -05:00
comfyanonymous
cca96a85ae
Fix cosmos VAE failing with videos longer than 121 frames.
2025-01-16 16:30:06 -05:00
comfyanonymous
619b8cde74
Bump ComfyUI version to 0.3.11
2025-01-16 14:54:48 -05:00
comfyanonymous
31831e6ef1
Code refactor.
2025-01-16 07:23:54 -05:00
comfyanonymous
88ceb28e20
Tweak hunyuan memory usage factor.
2025-01-16 06:31:03 -05:00
comfyanonymous
23289a6a5c
Clean up some debug lines.
2025-01-16 04:24:39 -05:00
comfyanonymous
9d8b6c1f46
More accurate memory estimation for cosmos and hunyuan video.
2025-01-16 03:48:40 -05:00
comfyanonymous
6320d05696
Slightly lower hunyuan video memory usage.
2025-01-16 00:23:01 -05:00
comfyanonymous
25683b5b02
Lower cosmos diffusion model memory usage.
2025-01-15 23:46:42 -05:00
comfyanonymous
4758fb64b9
Lower cosmos VAE memory usage by a bit.
2025-01-15 22:57:52 -05:00
comfyanonymous
008761166f
Optimize first attention block in cosmos VAE.
2025-01-15 21:48:46 -05:00
comfyanonymous
bfd5dfd611
3.13 doesn't work yet.
2025-01-15 20:32:44 -05:00
comfyanonymous
55ade36d01
Remove python 3.8 from test-build workflow.
2025-01-15 20:24:55 -05:00
comfyanonymous
2e20e399ea
Add minimum numpy version to requirements.txt
2025-01-15 20:19:56 -05:00
comfyanonymous
3baf92d120
CosmosImageToVideoLatent batch_size now does something.
2025-01-15 17:19:59 -05:00
comfyanonymous
1709a8441e
Use latest python 3.12.8 the portable release.
2025-01-15 14:50:40 -05:00
comfyanonymous
cba58fff0b
Remove unsafe embedding load for very old pytorch.
2025-01-15 04:32:23 -05:00
comfyanonymous
2feb8d0b77
Force safe loading of files in torch format on pytorch 2.4+
...
If this breaks something for you make an issue.
2025-01-15 03:50:27 -05:00
comfyanonymous
5b657f8c15
Allow setting start and end image in CosmosImageToVideoLatent.
2025-01-15 00:41:35 -05:00
comfyanonymous
3aaabb12d4
Implement Cosmos Image/Video to World (Video) diffusion models.
...
Use CosmosImageToVideoLatent to set the input image/video.
2025-01-14 05:14:10 -05:00
comfyanonymous
1f1c7b7b56
Remove useless code.
2025-01-13 03:52:37 -05:00
comfyanonymous
90f349f93d
Add res_multistep sampler from the cosmos code.
...
This sampler should work with all models.
2025-01-12 03:10:07 -05:00
comfyanonymous
ee8a7ab69d
Fast latent preview for Cosmos.
2025-01-11 04:41:24 -05:00
comfyanonymous
adea2beb5c
Add edm option to ModelSamplingContinuousEDM for Cosmos.
...
You can now use this node with "edm" selected to control the sigma_max and
sigma_min of the Cosmos model sampling.
2025-01-11 02:18:42 -05:00
comfyanonymous
2ff3104f70
WIP support for Nvidia Cosmos 7B and 14B text to world (video) models.
2025-01-10 09:14:16 -05:00
comfyanonymous
129d8908f7
Add argument to skip the output reshaping in the attention functions.
2025-01-10 06:27:37 -05:00
comfyanonymous
ff838657fa
Cleaner handling of attention mask in ltxv model code.
2025-01-09 07:12:03 -05:00
comfyanonymous
2307ff6746
Improve some logging messages.
2025-01-08 19:05:22 -05:00
comfyanonymous
d0f3752e33
Properly calculate inner dim for t5 model.
...
This is required to support some different types of t5 models.
2025-01-07 17:33:03 -05:00
comfyanonymous
4209edf48d
Make a few more samplers deterministic.
2025-01-07 02:12:32 -05:00
comfyanonymous
916d1e14a9
Make ancestral samplers more deterministic.
2025-01-06 03:04:32 -05:00
comfyanonymous
c8a3492c22
Make the device an optional parameter in the clip loaders.
2025-01-05 04:29:36 -05:00
comfyanonymous
5cbf79787f
Add advanced device option to clip loader nodes.
...
Right click the "Load CLIP" or DualCLIPLoader node and "Show Advanced".
2025-01-05 01:46:11 -05:00
comfyanonymous
d45ebb63f6
Remove old unused function.
2025-01-04 07:20:54 -05:00
comfyanonymous
8f29664057
Change defaults in nightly package workflow.
2025-01-03 12:12:17 -05:00
comfyanonymous
9e9c8a1c64
Clear cache as often on AMD as Nvidia.
...
I think the issue this was working around has been solved.
If you notice that this change slows things down or causes stutters on
your AMD GPU with ROCm on Linux please report it.
2025-01-02 08:44:16 -05:00
comfyanonymous
79eea51a1d
Fix and enforce all ruff W rules.
2025-01-01 03:08:33 -05:00
comfyanonymous
b7572b2f87
Fix and enforce no trailing whitespace.
2024-12-31 03:16:37 -05:00
comfyanonymous
d9b7cfac7e
Fix and enforce new lines at the end of files.
2024-12-30 04:14:59 -05:00
comfyanonymous
a618f768e0
Auto reshape 2d to 3d latent for single image generation on video model.
2024-12-29 02:26:49 -05:00
comfyanonymous
e1dec3c792
Fix formatting.
2024-12-28 05:33:17 -05:00
comfyanonymous
b504bd606d
Add ruff rule for empty line with trailing whitespace.
2024-12-28 05:23:08 -05:00
comfyanonymous
d170292594
Remove some trailing white space.
2024-12-27 18:02:30 -05:00
comfyanonymous
4b5bcd8ac4
Closer memory estimation for hunyuan dit model.
2024-12-27 07:37:00 -05:00
comfyanonymous
ceb50b2cbf
Closer memory estimation for pixart models.
2024-12-27 07:30:09 -05:00
comfyanonymous
160ca08138
Use python 3.9 in launch test instead of 3.8
...
Fix ruff check.
2024-12-26 20:05:54 -05:00
comfyanonymous