| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Add support for `--upcast-sampling` with SD XL | brkirch | 2023-07-18 | 1 | -1/+7 |
| | | |||||
| * | Fix up string formatting/concatenation to f-strings where feasible | Aarni Koskela | 2023-05-09 | 1 | -1/+1 |
| | | |||||
| * | Update sd_hijack_unet.py | FNSpd | 2023-03-24 | 1 | -1/+1 |
| | | |||||
| * | Update sd_hijack_unet.py | FNSpd | 2023-03-21 | 1 | -1/+1 |
| | | |||||
| * | Apply hijacks in ddpm_edit for upcast sampling | brkirch | 2023-02-08 | 1 | -0/+11 |
| | | | | | To avoid import errors, ddpm_edit hijacks are done after an instruct pix2pix model is loaded. | ||||
| * | Refactor conditional casting, fix upscalers | brkirch | 2023-01-28 | 1 | -1/+7 |
| | | |||||
| * | fix for unet hijack breaking the train tab | AUTOMATIC | 2023-01-25 | 1 | -2/+5 |
| | | |||||
| * | Add option for float32 sampling with float16 UNet | brkirch | 2023-01-25 | 1 | -0/+29 |
| | | | | | This also handles type casting so that ROCm and MPS torch devices work correctly without --no-half. One cast is required for deepbooru in deepbooru_model.py, some explicit casting is required for img2img and inpainting. depth_model can't be converted to float16 or it won't work correctly on some systems (it's known to have issues on MPS) so in sd_models.py model.depth_model is removed for model.half(). | ||||
| * | Fix various typos | Jim Hays | 2022-12-15 | 1 | -1/+1 |
| | | |||||
| * | do not replace entire unet for the resolution hack | AUTOMATIC | 2022-12-10 | 1 | -0/+30 |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |