| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2022-09-29 | Holy $hit. | d8ahazard | |
| Yep. Fix gfpgan_model_arch requirement(s). Add Upscaler base class, move from images. Add a lot of methods to Upscaler. Re-work all the child upscalers to be proper classes. Add BSRGAN scaler. Add ldsr_model_arch class, removing the dependency for another repo that just uses regular latent-diffusion stuff. Add one universal method that will always find and load new upscaler models without having to add new "setup_model" calls. Still need to add command line params, but that could probably be automated. Add a "self.scale" property to all Upscalers so the scalers themselves can do "things" in response to the requested upscaling size. Ensure LDSR doesn't get stuck in a longer loop of "upscale/downscale/upscale" as we try to reach the target upscale size. Add typehints for IDE sanity. PEP-8 improvements. Moar. | |||
| 2022-09-27 | add missing s_tmax | DepFA | |
| 2022-09-27 | pass eta to tex2img sampler | DepFA | |
| 2022-09-27 | take extra sampler properties from StableDiffusionProcessing | DepFA | |
| 2022-09-27 | pass extra KDiffusionSampler function parameters | DepFA | |
| 2022-09-27 | pass ddim_eta and ddim_discretize | DepFA | |
| 2022-09-19 | added highres fix feature | AUTOMATIC | |
| 2022-09-18 | fixed a bug with seed reproducibility with bacth_size>0 and bacth_count>0 | AUTOMATIC | |
| 2022-09-16 | an option to do exactly the amount of specified steps in img2img | AUTOMATIC | |
| 2022-09-16 | Merge branch 'batch-seed-attempt' | AUTOMATIC | |
| 2022-09-16 | prevent replacing torch_randn globally (instead replacing ↵ | AUTOMATIC | |
| k_diffusion.sampling.torch) and add a setting to disable this all | |||
| 2022-09-16 | Prompt editing only applies to images in first batch of desired batch size ↵ | AUTOMATIC | |
| when batch count > 1 #535 | |||
| 2022-09-15 | Merge branch 'prompt_editing' | AUTOMATIC | |
| 2022-09-15 | quantization off by default | AUTOMATIC | |
| 2022-09-15 | Respect quantization setting | C43H66N12O12S2 | |
| 2022-09-15 | Construct CompVisDenoiser with quantization | C43H66N12O12S2 | |
| 2022-09-15 | prompt editing | AUTOMATIC | |
| 2022-09-13 | first attempt to produce crrect seeds in batch | AUTOMATIC | |
| 2022-09-13 | bandaid for broken ddim sampling #389 | AUTOMATIC | |
| 2022-09-12 | Noisy image previews #257 | AUTOMATIC | |
| 2022-09-08 | fix for PLMS live previews in txt2img | AUTOMATIC | |
| 2022-09-08 | fix for DDIM live previews in txt2img | AUTOMATIC | |
| 2022-09-08 | More informative progress printing | JohannesGaessler | |
| 2022-09-07 | big improvements to inpainting and outpainting | AUTOMATIC | |
| 2022-09-06 | fix for live progress breaking lowvram and medvram optimizations | AUTOMATIC | |
| 2022-09-06 | added preview option | AUTOMATIC | |
| 2022-09-06 | added progressbar | AUTOMATIC | |
| added an option to disable progressbar added interrupt support to DDIM/PLMS | |||
| 2022-09-03 | support for scripts | AUTOMATIC | |
| 2022-09-03 | split codebase into multiple files; to anyone this affects negatively: sorry | AUTOMATIC | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiff |