| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 2023-03-11 | Merge pull request #8017 from space-nuko/before-process-batch | AUTOMATIC1111 | |
| Add `before_process_batch` script callback | |||
| 2023-03-10 | Merge remote-tracking branch 'origin/master' into unipc | space-nuko | |
| 2023-03-10 | Negative prompt fix | InvincibleDude | |
| 2023-03-04 | Fix crash when hr is disabled | InvincibleDude | |
| 2023-03-03 | Merge branch 'master' into improved-hr-conflict-test | InvincibleDude | |
| 2023-03-03 | Image processing changes | InvincibleDude | |
| Image processing changes | |||
| 2023-02-22 | Add before_process_batch script callback | space-nuko | |
| 2023-02-19 | fix the a merge conflict resolve i did that entirely breaks image generation | AUTOMATIC | |
| 2023-02-19 | Merge branch 'master' into fix-save-params-2 | AUTOMATIC1111 | |
| 2023-02-16 | Fix params.txt saving for infotexts modified by process_batch | space-nuko | |
| 2023-02-13 | Apply extra networks per-batch instead of per-session (fixes wildcards) | space-nuko | |
| 2023-02-10 | bug fix | space-nuko | |
| 2023-02-10 | UniPC does not support img2img (for now) | space-nuko | |
| 2023-02-10 | Working UniPC (for batch size 1) | space-nuko | |
| 2023-02-05 | Image info fix | InvincibleDude | |
| 2023-02-05 | Merge branch 'AUTOMATIC1111:master' into improved-hr-conflict-test | InvincibleDude | |
| 2023-02-03 | txt2img Hires Fix | Kyle | |
| 2023-02-03 | Image CFG Added (Full Implementation) | Kyle | |
| Uses separate denoiser for edit (instruct-pix2pix) models No impact to txt2img or regular img2img "Image CFG Scale" will only apply to instruct-pix2pix models and metadata will only be added if using such model | |||
| 2023-02-02 | Processing only, no CFGDenoiser change | Kyle | |
| Allows instruct-pix2pix | |||
| 2023-02-02 | Revert "instruct-pix2pix support" | Kyle | |
| This reverts commit 269833067de1e7d0b6a6bd65724743d6b88a133f. | |||
| 2023-02-02 | instruct-pix2pix support | Kyle | |
| 2023-01-30 | Merge branch 'master' into improved-hr-conflict-test | InvincibleDude | |
| 2023-01-30 | make the program read Eta and Eta DDIM from generation parameters | AUTOMATIC | |
| 2023-01-29 | Extra network in hr abomination fix | invincibledude | |
| 2023-01-29 | Extra networks loading fix | invincibledude | |
| 2023-01-29 | Extra networks loading fix | invincibledude | |
| 2023-01-29 | Extra networks loading fix | invincibledude | |
| 2023-01-29 | Merge branch 'master' into master | InvincibleDude | |
| 2023-01-29 | remove Batch size and Batch pos from textinfo (goodbye) | AUTOMATIC | |
| 2023-01-28 | Merge pull request #7309 from brkirch/fix-embeddings | AUTOMATIC1111 | |
| Fix embeddings, upscalers, and refactor `--upcast-sampling` | |||
| 2023-01-28 | Refactor conditional casting, fix upscalers | brkirch | |
| 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 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiff |