wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-07-21 23:41:28 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity
3,372 Commits 305 Branches 166 Tags
da70ccc210f7e5b4ee5768564b7c24d32e5e790c
Commit Graph
1478 Commits
Author SHA1 Message Date
comfyanonymous f82314fcfc Fix duplicate sigmas on beta scheduler. 2024-10-21 20:19:45 -04:00
comfyanonymous 0075c6d096 Mixed precision diffusion models with scaled fp8. 
This change allows supports for diffusion models where all the linears are
scaled fp8 while the other weights are the original precision.
 2024-10-21 18:12:51 -04:00
patientxandGitHub 9fd46200ab Merge branch 'comfyanonymous:master' into master 2024-10-21 12:23:49 +03:00
comfyanonymous 83ca891118 Support scaled fp8 t5xxl model. 2024-10-20 22:27:00 -04:00
patientxandGitHub 5a425aeda1 Merge branch 'comfyanonymous:master' into master 2024-10-20 21:06:24 +03:00
comfyanonymous f9f9faface Fixed model merging issue with scaled fp8. 2024-10-20 06:24:31 -04:00
patientxandGitHub 1678ea8f9c Merge branch 'comfyanonymous:master' into master 2024-10-20 10:20:06 +03:00
comfyanonymous 471cd3eace fp8 casting is fast on GPUs that support fp8 compute. 2024-10-20 00:54:47 -04:00
comfyanonymous a68bbafddb Support diffusion models with scaled fp8 weights. 2024-10-19 23:47:42 -04:00
comfyanonymous 73e3a9e676 Clamp output when rounding weight to prevent Nan. 2024-10-19 19:07:10 -04:00
patientxandGitHub d4b509799f Merge branch 'comfyanonymous:master' into master 2024-10-18 11:14:20 +03:00
comfyanonymous 67158994a4 Use the lowvram cast_to function for everything. 2024-10-17 17:25:56 -04:00
patientxandGitHub fc4acf26c3 Merge branch 'comfyanonymous:master' into master 2024-10-16 23:54:39 +03:00
comfyanonymous 0bedfb26af Revert "Fix Transformers FutureWarning (#5140)" 
This reverts commit 95b7cf9bbe.
 2024-10-16 12:36:19 -04:00
patientxandGitHub f143a803d6 Merge branch 'comfyanonymous:master' into master 2024-10-15 09:55:21 +03:00
comfyanonymous f584758271 Cleanup some useless lines. 2024-10-14 21:02:39 -04:00
svdcandGitHub 95b7cf9bbe Fix Transformers FutureWarning (#5140) 
* Update sd1_clip.py

Fix Transformers FutureWarning

* Update sd1_clip.py

Fix comment
 2024-10-14 20:12:20 -04:00
patientxandGitHub a5e3eae103 Merge branch 'comfyanonymous:master' into master 2024-10-12 23:00:55 +03:00
comfyanonymous 3c60ecd7a8 Fix fp8 ops staying enabled. 2024-10-12 14:10:13 -04:00
comfyanonymous 7ae6626723 Remove useless argument. 2024-10-12 07:16:21 -04:00
patientxandGitHub eae1c15ab1 Merge branch 'comfyanonymous:master' into master 2024-10-12 11:02:28 +03:00
comfyanonymous 6632365e16 model_options consistency between functions. 
weight_dtype -> dtype
 2024-10-11 20:51:19 -04:00
Kadir NarandGitHub ad07796777 🐛 Add device to variable c (#5210) 2024-10-11 20:37:50 -04:00
patientxandGitHub e4d24788f1 Merge branch 'comfyanonymous:master' into master 2024-10-11 00:22:45 +03:00
comfyanonymous 1b80895285 Make clip loader nodes support loading sd3 t5xxl in lower precision. 
Add attention mask support in the SD3 text encoder code.
 2024-10-10 15:06:15 -04:00
patientxandGitHub f9eab05f54 Merge branch 'comfyanonymous:master' into master 2024-10-10 10:30:17 +03:00
Dr.Lt.DataandGitHub 5f9d5a244b Hotfix for the div zero occurrence when memory_used_encode is 0 (#5121) 
https://github.com/comfyanonymous/ComfyUI/issues/5069#issuecomment-2382656368
 2024-10-09 23:34:34 -04:00
Jonathan AvilaandGitHub 4b2f0d9413 Increase maximum macOS version to 15.0.1 when forcing upcast attention (#5191) 2024-10-09 22:21:41 -04:00
comfyanonymous e38c94228b Add a weight_dtype fp8_e4m3fn_fast to the Diffusion Model Loader node. 
This is used to load weights in fp8 and use fp8 matrix multiplication.
 2024-10-09 19:43:17 -04:00
patientxandGitHub 21d9bef158 Merge branch 'comfyanonymous:master' into master 2024-10-09 11:22:05 +03:00
comfyanonymous 203942c8b2 Fix flux doras with diffusers keys. 2024-10-08 19:03:40 -04:00
patientxandGitHub df174b7cbd Merge branch 'comfyanonymous:master' into master 2024-10-07 22:22:38 +03:00
comfyanonymous 8dfa0cc552 Make SD3 fast previews a little better. 2024-10-07 09:19:59 -04:00
patientxandGitHub 445390eae2 Merge branch 'comfyanonymous:master' into master 2024-10-07 10:15:48 +03:00
comfyanonymous e5ecdfdd2d Make fast previews for SDXL a little better by adding a bias. 2024-10-06 19:27:04 -04:00
comfyanonymous 7d29fbf74b Slightly improve the fast previews for flux by adding a bias. 2024-10-06 17:55:46 -04:00
patientxandGitHub dfa888ea5e Merge branch 'comfyanonymous:master' into master 2024-10-05 21:09:30 +03:00
comfyanonymous 7d2467e830 Some minor cleanups. 2024-10-05 13:22:39 -04:00
patientxandGitHub 613a320875 Merge branch 'comfyanonymous:master' into master 2024-10-05 00:01:10 +03:00
comfyanonymous 6f021d8aa0 Let --verbose have an argument for the log level. 2024-10-04 10:05:34 -04:00
patientxandGitHub 9ec6b86747 Merge branch 'comfyanonymous:master' into master 2024-10-03 22:16:09 +03:00
comfyanonymous d854ed0bcf Allow using SD3 type te output on flux model. 2024-10-03 09:44:54 -04:00
comfyanonymous abcd006b8c Allow more permutations of clip/t5 in dual clip loader. 2024-10-03 09:26:11 -04:00
patientxandGitHub 4c9c09b888 Merge branch 'comfyanonymous:master' into master 2024-10-02 13:35:22 +03:00
comfyanonymous d985d1d7dc CLIP Loader node now supports clip_l and clip_g only for SD3. 2024-10-02 04:25:17 -04:00
patientxandGitHub 8e0250f3d1 Merge branch 'comfyanonymous:master' into master 2024-10-01 19:40:37 +03:00
comfyanonymous d1cdf51e1b Refactor some of the TE detection code. 2024-10-01 07:08:41 -04:00
patientxandGitHub 305c31142b Merge branch 'comfyanonymous:master' into master 2024-10-01 11:55:23 +03:00
comfyanonymous b4626ab93e Add simpletuner lycoris format for SD unet. 2024-09-30 06:03:27 -04:00
patientxandGitHub fa20ab0287 Merge branch 'comfyanonymous:master' into master 2024-09-29 23:53:36 +03:00