comfyanonymous
79d5ceae6e
Improved memory management. ( #5450 )
...
* Less fragile memory management.
* Fix issue.
* Remove useless function.
* Prevent and detect some types of memory leaks.
* Run garbage collector when switching workflow if needed.
* Fix issue.
2024-12-02 14:39:34 -05:00
comfyanonymous
2d5b3e0078
Remove useless code.
2024-12-02 06:49:55 -05:00
patientx
74e6ad95f7
Merge branch 'comfyanonymous:master' into master
2024-12-01 18:49:39 +03:00
comfyanonymous
8e4118c0de
make dpm_2_ancestral work with rectified flow.
2024-12-01 07:37:41 -05:00
patientx
f7d377433e
Merge pull request #45 from CodeDruidX/patch-1
...
Update fixforrx580.bat
2024-11-30 16:53:11 +03:00
patientx
b1a06fa2a4
Merge branch 'comfyanonymous:master' into master
2024-11-30 16:51:24 +03:00
CodeDruidX
4af7c7d5d5
Update fixforrx580.bat
...
Add venv activation to downgrade the proper torch installation
2024-11-30 20:24:50 +07:00
comfyanonymous
3fc6ebcdd7
Add basic style model "multiply" strength.
2024-11-30 07:27:11 -05:00
patientx
2e2c775e8d
Update README.md
2024-11-29 14:59:50 +03:00
patientx
ec967d39d8
Merge branch 'comfyanonymous:master' into master
2024-11-29 14:59:13 +03:00
patientx
5497e3b694
Update README.md
2024-11-29 14:59:04 +03:00
comfyanonymous
20a560eb97
How to enable experimental memory efficient attention on ROCm RDNA3.
2024-11-29 06:19:49 -05:00
patientx
47c9391ea0
Merge branch 'comfyanonymous:master' into master
2024-11-29 13:34:26 +03:00
Dr.Lt.Data
82c5308561
Backward compatibility patch for changes in the method signature of InpaintModelConditioning. ( #5825 )
...
https://github.com/comfyanonymous/ComfyUI/issues/5813
2024-11-28 20:30:28 -05:00
comfyanonymous
26fb2c68e8
Add a way to disable cropping in the CLIPVisionEncode node.
2024-11-28 20:24:47 -05:00
patientx
614889a36b
Merge branch 'comfyanonymous:master' into master
2024-11-28 16:00:16 +03:00
comfyanonymous
bf2650a80e
Fast previews for ltxv.
2024-11-28 06:46:15 -05:00
patientx
b30020ae6b
Merge branch 'comfyanonymous:master' into master
2024-11-28 14:19:31 +03:00
Chenlei Hu
53646e0f32
Update web content to release v1.4.13 ( #5807 )
2024-11-28 04:59:06 -05:00
Chenlei Hu
20879c78f9
Remove internal model download endpoint ( #5432 )
2024-11-28 04:57:06 -05:00
comfyanonymous
b666539595
Remove print.
2024-11-27 20:28:39 -05:00
patientx
79029da19e
Merge branch 'comfyanonymous:master' into master
2024-11-28 01:59:08 +03:00
comfyanonymous
95d8713482
Missing parentheses.
2024-11-27 13:45:32 -05:00
patientx
88602732f4
Merge branch 'comfyanonymous:master' into master
2024-11-27 10:29:52 +03:00
comfyanonymous
0d4e29f13f
LTXV model merging node.
2024-11-27 01:43:31 -05:00
patientx
234ec9aa01
Merge branch 'comfyanonymous:master' into master
2024-11-27 02:09:20 +03:00
comfyanonymous
497db6212f
Alternative fix for #5767
2024-11-26 17:53:04 -05:00
lky
24dc581dc3
fix multi add makedirs error ( #5786 )
...
try to start multiple comfyui server at the same time, and this got error
2024-11-26 15:34:19 -05:00
patientx
8f848c9e8b
Merge branch 'comfyanonymous:master' into master
2024-11-26 23:27:29 +03:00
comfyanonymous
4c82741b54
Support official SD3.5 Controlnets.
2024-11-26 11:31:25 -05:00
patientx
9fe09c02c2
Merge branch 'comfyanonymous:master' into master
2024-11-26 11:50:33 +03:00
comfyanonymous
15c39ea757
Support for the official mochi lora format.
2024-11-26 03:34:36 -05:00
comfyanonymous
b7143b74ce
Flux inpaint model does not work in fp16.
2024-11-26 01:33:01 -05:00
patientx
fc8f411fa8
Merge branch 'comfyanonymous:master' into master
2024-11-25 13:31:28 +03:00
comfyanonymous
61196d8857
Add option to inference the diffusion model in fp32 and fp64.
2024-11-25 05:00:23 -05:00
patientx
b5a8f208e5
Update README.md
2024-11-24 15:13:48 +03:00
patientx
91fe7d8c44
Update README.md
2024-11-24 15:12:39 +03:00
patientx
185f3868f6
Update README.md
2024-11-24 14:53:45 +03:00
patientx
2ab6c68377
Merge branch 'comfyanonymous:master' into master
2024-11-24 14:53:09 +03:00
patientx
d93171fa01
Update README.md
2024-11-24 14:53:02 +03:00
comfyanonymous
b4526d3fc3
Skip layer guidance now works on hydit model.
2024-11-24 05:54:30 -05:00
40476
3d802710e7
Update README.md ( #5707 )
2024-11-24 04:12:07 -05:00
spacepxl
7126ecffde
set LTX min length to 1 for t2i ( #5750 )
...
At length=1, the LTX model can do txt2img and img2img with no other changes required.
2024-11-23 21:33:08 -05:00
patientx
3479eb5cb2
Merge branch 'comfyanonymous:master' into master
2024-11-23 22:20:28 +03:00
comfyanonymous
ab885b33ba
Skip layer guidance node now works on LTX-Video.
2024-11-23 10:33:05 -05:00
patientx
63b7bfe64d
Merge branch 'comfyanonymous:master' into master
2024-11-23 13:22:15 +03:00
comfyanonymous
839ed3368e
Some improvements to the lowvram unloading.
2024-11-22 20:59:15 -05:00
patientx
d877db2b77
Merge branch 'comfyanonymous:master' into master
2024-11-23 02:50:32 +03:00
comfyanonymous
6e8cdcd3cb
Fix some tiled VAE decoding issues with LTX-Video.
2024-11-22 18:00:34 -05:00
comfyanonymous
e5c3f4b87f
LTXV lowvram fixes.
2024-11-22 17:17:11 -05:00