| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2023-01-25 | Add UI setting for upcasting attention to float32 | brkirch | -2/+2 | |
| Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers. In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also. | ||||
| 2023-01-09 | Remove fallback for Protocol import and remove Protocol import and remove ↵ | AUTOMATIC | -8/+11 | |
| instances of Protocol in code add some whitespace between functions to be in line with other code in the repo | ||||
| 2023-01-07 | Add fallback for Protocol import | ProGamerGov | -1/+7 | |
| 2023-01-06 | Added license | brkirch | -1/+1 | |
| 2023-01-06 | Use narrow instead of dynamic_slice | brkirch | -15/+19 | |
| 2023-01-06 | Add Birch-san's sub-quadratic attention implementation | brkirch | -0/+201 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |