| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2023-01-25 | Add UI setting for upcasting attention to float32 | brkirch | -1/+1 | |
| 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 | -7/+8 | |
| 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(). | ||||
| 2023-01-23 | Fix different first gen with Approx NN previews | brkirch | -1/+5 | |
| 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 | enable compact view for train tab | AUTOMATIC | -2/+6 | |
| prevent previews from ruining hypernetwork training | ||||
| 2023-01-21 | extract extra network data from prompt earlier | AUTOMATIC | -2/+2 | |
| 2023-01-21 | make it so that extra networks are not removed from infotext | AUTOMATIC | -1/+3 | |
| 2023-01-21 | extra networks UI | AUTOMATIC | -11/+13 | |
| 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 | -4/+4 | |
| Saves Extra Generation Parameters to params.txt | ||||
| 2023-01-18 | use DDIM in hires fix is the sampler is PLMS | AUTOMATIC | -1/+2 | |
| 2023-01-17 | Changed params.txt save to after manual init call | EllangoK | -4/+4 | |
| 2023-01-16 | make StableDiffusionProcessing class not hold a reference to shared.sd_model ↵ | AUTOMATIC | -4/+5 | |
| object | ||||
| 2023-01-16 | Add a check and explanation for tensor with all NaNs. | AUTOMATIC | -0/+3 | |
| 2023-01-14 | change hypernets to use sha256 hashes | AUTOMATIC | -1/+1 | |
| 2023-01-12 | Fix extension parameters not being saved to last used parameters | space-nuko | -4/+4 | |
| 2023-01-09 | add an option to use old hiresfix width/height behavior | AUTOMATIC | -2/+24 | |
| add a visual effect to inactive hires fix elements | ||||
| 2023-01-07 | Merge branch 'AUTOMATIC1111:master' into img2img-api-scripts | noodleanon | -1/+0 | |
| 2023-01-07 | rework hires fix preview for #6437: movie it to where it takes less place, ↵ | AUTOMATIC | -1/+0 | |
| make it actually account for all relevant sliders and calculate dimensions correctly | ||||
| 2023-01-05 | allow img2img api to run scripts | noodleanon | -2/+2 | |
| 2023-01-05 | experimental optimization | AUTOMATIC | -3/+25 | |
| 2023-01-05 | move sd_model assignment to the place where we change the sd_model | AUTOMATIC | -5/+9 | |
| 2023-01-05 | Merge branch 'AUTOMATIC1111:master' into fix-sd-arch-switch-in-override-settings | Philpax | -67/+113 | |
| 2023-01-05 | make hires fix not do anything if the user chooses the second pass ↵ | AUTOMATIC | -8/+17 | |
| 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 | -3/+6 | |
| progress bars | ||||
| 2023-01-04 | added the option to specify target resolution with possibility of truncating ↵ | AUTOMATIC | -5/+46 | |
| for hires fix; also sampling steps | ||||
| 2023-01-04 | add XY plot parameters to grid image and do not add them to individual images | AUTOMATIC | -1/+1 | |
| 2023-01-04 | use shared function from processing for creating dummy mask when training ↵ | AUTOMATIC | -19/+20 | |
| inpainting model | ||||
| 2023-01-04 | add infotext to "-before-highres-fix" images | AUTOMATIC | -1/+5 | |
| 2023-01-04 | Merge pull request #6299 from stysmmaker/feat/latent-upscale-modes | AUTOMATIC1111 | -1/+1 | |
| Add more latent upscale modes | ||||
| 2023-01-04 | Update processing.py | MMaker | -1/+1 | |
| 2023-01-04 | fix: Save full res of intermediate step | MMaker | -1/+1 | |
| 2023-01-03 | fix hires fix not working in API when user does not specify upscaler | AUTOMATIC | -1/+1 | |
| 2023-01-02 | Hires fix rework | AUTOMATIC | -41/+27 | |
| 2022-12-31 | make it so that memory/embeddings info is displayed in a separate UI element ↵ | AUTOMATIC | -2/+3 | |
| from generation parameters, and is preserved when you change the displayed infotext by clicking on gallery images | ||||
| 2022-12-26 | make it so that blank ENSD does not break image generation | AUTOMATIC | -3/+4 | |
| 2022-12-25 | fix(api): assign sd_model after settings change | Philpax | -2/+4 | |
| 2022-12-24 | Merge pull request #5718 from space-nuko/feature/save-hypernetwork-hash | AUTOMATIC1111 | -2/+3 | |
| Save hypernetwork hash and fix hypernetwork parameter restoring | ||||
| 2022-12-24 | rename the option for img2img latent upscale | AUTOMATIC | -1/+1 | |
| 2022-12-24 | Merge pull request #5521 from AndrewRyanChama/ryan/img2imglatentscale | AUTOMATIC1111 | -1/+5 | |
| Add latent upscale option to img2img | ||||
| 2022-12-24 | Merge pull request #5873 from philpax/override-settings-restore-afterwards | AUTOMATIC1111 | -7/+10 | |
| feat(api): add override_settings_restore_afterwards | ||||
| 2022-12-24 | Merge pull request #5753 from calvinballing/master | AUTOMATIC1111 | -7/+7 | |
| Fix various typos | ||||
| 2022-12-24 | add an option for img2img background color | AUTOMATIC | -1/+1 | |
| 2022-12-20 | feat(api): add override_settings_restore_afterwards | Philpax | -13/+16 | |
| 2022-12-14 | Fix various typos | Jim Hays | -7/+7 | |
| 2022-12-13 | Save hypernetwork hash in infotext | space-nuko | -2/+3 | |
| 2022-12-11 | Improve color correction with luminosity blend | ThereforeGames | -3/+6 | |
| 2022-12-10 | Merge pull request #5191 from ↵ | AUTOMATIC1111 | -2/+8 | |
| aliencaocao/enable_checkpoint_switching_in_override_settings Support changing checkpoint and vae through override_settings | ||||
| 2022-12-10 | remove NSFW filter and its dependency; if you still want it, find it in the ↵ | AUTOMATIC | -4/+3 | |
| extensions section | ||||
| 2022-12-10 | add Noise multiplier option to infotext | AUTOMATIC | -2/+6 | |
| 2022-12-10 | Merge pull request #5373 from mezotaken/master | AUTOMATIC1111 | -0/+1 | |
| add noise strength parameter similar to NAI | ||||
| 2022-12-08 | Depth2img model support | Jay Smith | -4/+34 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |