| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2023-01-27 | add data-dir flag and set all user data directories based on it | Max Audron | |
| 2023-01-26 | add an option to enable sections from extras tab in txt2img/img2img | AUTOMATIC | |
| fix some style inconsistenices | |||
| 2023-01-26 | Fix full previews, --no-half-vae | brkirch | |
| 2023-01-25 | add edit_image_conditioning from my earlier edits in case there's an attempt ↵ | AUTOMATIC | |
| to inegrate pix2pix properly this allows to use pix2pix model in img2img though it won't work well this way | |||
| 2023-01-25 | Merge pull request #6510 from brkirch/unet16-upcast-precision | AUTOMATIC1111 | |
| Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half | |||
| 2023-01-25 | change to code for live preview fix on OSX to be bit more obvious | AUTOMATIC | |
| 2023-01-25 | Add UI setting for upcasting attention to float32 | brkirch | |
| 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. | |||
| 2023-01-25 | Add option for float32 sampling with float16 UNet | brkirch | |
| 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(). | |||
| 2023-01-24 | Merge branch 'AUTOMATIC1111:master' into master | InvincibleDude | |
| 2023-01-23 | Fix different first gen with Approx NN previews | brkirch | |
| The loading of the model for approx nn live previews can change the internal state of PyTorch, resulting in a different image. This can be avoided by preloading the approx nn model in advance. | |||
| 2023-01-22 | Gen params paste improvement | invincibledude | |
| 2023-01-22 | Gen params paste improvement | invincibledude | |
| 2023-01-22 | UI and PNG info improvements | invincibledude | |
| 2023-01-22 | UI and PNG info improvements | invincibledude | |
| 2023-01-22 | hr conditioning | invincibledude | |
| 2023-01-22 | hr conditioning | invincibledude | |
| 2023-01-22 | hr conditioning | invincibledude | |
| 2023-01-22 | hr conditioning | invincibledude | |
| 2023-01-22 | hr conditioning | invincibledude | |
| 2023-01-22 | hr conditioning | invincibledude | |
| 2023-01-22 | Hr-fix separate prompt experimentation | invincibledude | |
| 2023-01-22 | Logging for debugging | invincibledude | |
| 2023-01-22 | Fix | invincibledude | |
| 2023-01-22 | Hr separate prompt test | invincibledude | |
| 2023-01-22 | PLMS edge-case handling fix 5 | invincibledude | |
| 2023-01-22 | PLMS edge-case handling fix 3 | invincibledude | |
| 2023-01-22 | PLMS edge-case handling fix 2 | invincibledude | |
| 2023-01-22 | PLMS edge-case handling fix | invincibledude | |
| 2023-01-22 | enable compact view for train tab | AUTOMATIC | |
| prevent previews from ruining hypernetwork training | |||
| 2023-01-21 | Type mismatch fix | invincibledude | |
| 2023-01-21 | First test of different sampler for hi-res fix | invincibledude | |
| 2023-01-21 | extract extra network data from prompt earlier | AUTOMATIC | |
| 2023-01-21 | make it so that extra networks are not removed from infotext | AUTOMATIC | |
| 2023-01-21 | extra networks UI | AUTOMATIC | |
| rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight> | |||
| 2023-01-18 | Merge pull request #6854 from EllangoK/master | AUTOMATIC1111 | |
| Saves Extra Generation Parameters to params.txt | |||
| 2023-01-18 | use DDIM in hires fix is the sampler is PLMS | AUTOMATIC | |
| 2023-01-17 | Changed params.txt save to after manual init call | EllangoK | |
| 2023-01-16 | make StableDiffusionProcessing class not hold a reference to shared.sd_model ↵ | AUTOMATIC | |
| object | |||
| 2023-01-16 | Add a check and explanation for tensor with all NaNs. | AUTOMATIC | |
| 2023-01-14 | change hypernets to use sha256 hashes | AUTOMATIC | |
| 2023-01-12 | Fix extension parameters not being saved to last used parameters | space-nuko | |
| 2023-01-09 | add an option to use old hiresfix width/height behavior | AUTOMATIC | |
| add a visual effect to inactive hires fix elements | |||
| 2023-01-07 | Merge branch 'AUTOMATIC1111:master' into img2img-api-scripts | noodleanon | |
| 2023-01-07 | rework hires fix preview for #6437: movie it to where it takes less place, ↵ | AUTOMATIC | |
| make it actually account for all relevant sliders and calculate dimensions correctly | |||
| 2023-01-05 | allow img2img api to run scripts | noodleanon | |
| 2023-01-05 | experimental optimization | AUTOMATIC | |
| 2023-01-05 | move sd_model assignment to the place where we change the sd_model | AUTOMATIC | |
| 2023-01-05 | Merge branch 'AUTOMATIC1111:master' into fix-sd-arch-switch-in-override-settings | Philpax | |
| 2023-01-05 | make hires fix not do anything if the user chooses the second pass ↵ | AUTOMATIC | |
| resolution to be the same as first pass resolution | |||
| 2023-01-04 | fix incorrect display/calculation for number of steps for hires fix in ↵ | AUTOMATIC | |
| progress bars | |||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiff |