| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2022-10-02 | initial support for training textual inversion | AUTOMATIC | -299/+717 | |
| 2022-09-30 | ALT + return will submit prompt when it's in focus | Trung Ngo | -1/+1 | |
| 2022-09-30 | remove extra print from BSRGAN | AUTOMATIC | -1/+0 | |
| 2022-09-30 | Merge pull request #1371 from d8ahazard/master | AUTOMATIC1111 | -7/+17 | |
| Fix LDSR, BSRGAN, recursive SD checkpoint Loading | ||||
| 2022-09-30 | fix model checkpoint merger tab failing to save model | AUTOMATIC | -1/+3 | |
| 2022-09-30 | Merge branch 'master' into master | d8ahazard | -2/+3 | |
| 2022-09-30 | if --ckpt option is specified, load that model | AUTOMATIC | -1/+2 | |
| 2022-09-30 | Update bsrgan_model.py | d8ahazard | -1/+0 | |
| 2022-09-30 | Merge branch 'master' of https://github.com/d8ahazard/stable-diffusion-webui | d8ahazard | -11/+18 | |
| 2022-09-30 | Fix BSRGAN Model loading. | d8ahazard | -1/+2 | |
| 2022-09-30 | Merge branch 'master' into master | d8ahazard | -11/+18 | |
| 2022-09-30 | Merge remote-tracking branch 'origin/master' | AUTOMATIC | -1/+17 | |
| 2022-09-30 | hello #1109 | AUTOMATIC | -1/+1 | |
| 2022-09-30 | fix for one error with BSRGAN, though it fails to work anyway #1109 | AUTOMATIC | -2/+1 | |
| 2022-09-30 | change default inpaint mode to original | AUTOMATIC | -1/+1 | |
| 2022-09-30 | Set default value for ckpt-dir | d8ahazard | -1/+1 | |
| 2022-09-30 | Remove unused LDSR opt | d8ahazard | -1/+0 | |
| 2022-09-30 | Logging.... | d8ahazard | -1/+0 | |
| Cleanup. Sorry. | ||||
| 2022-09-30 | Fix recursive model loading | d8ahazard | -1/+3 | |
| Ensure we find checkpoints within subdirectories. | ||||
| 2022-09-30 | Fix BSRGAN variable not found. | d8ahazard | -2/+1 | |
| 2022-09-30 | Remove useless print message | d8ahazard | -1/+0 | |
| 2022-09-30 | Fix model paths, ensure we have the right files. | d8ahazard | -4/+8 | |
| Also, clean up logging in the ldsr arch file. | ||||
| 2022-09-30 | Remove LDSR project.yaml if too large. | d8ahazard | -0/+7 | |
| If we accidentally downloaded the wrong file and saved it as project.yaml, this will delete it so it can be re-downloaded. | ||||
| 2022-09-30 | Fix LDSR YAML path | d8ahazard | -1/+1 | |
| 2022-09-30 | prevent neural network resizing when it is not necessary #1109 | AUTOMATIC | -8/+10 | |
| 2022-09-30 | add embeddings dir | AUTOMATIC | -1/+6 | |
| 2022-09-30 | fixed so that {prompt} can be anywhere in style | RnDMonkey | -1/+5 | |
| 2022-09-30 | refined [styles] pattern and added [prompt_no_styles] | RnDMonkey | -1/+13 | |
| 2022-09-30 | return the dropdown that mysteriously disappeared | AUTOMATIC | -1/+1 | |
| 2022-09-30 | repair broken highres fix #1109 | AUTOMATIC | -3/+2 | |
| 2022-09-30 | revert the annotation not supported by old pythons | AUTOMATIC | -1/+1 | |
| 2022-09-30 | remove unwanted formatting/functionality from the PR | AUTOMATIC | -168/+125 | |
| 2022-09-30 | fix for broken codeformer in PR | AUTOMATIC | -1/+1 | |
| 2022-09-30 | undo upscaler model filename tampering | AUTOMATIC | -1/+0 | |
| 2022-09-30 | fix the bug with broken rescaling in PR | AUTOMATIC | -4/+12 | |
| 2022-09-30 | fix bugs in the PR | AUTOMATIC | -2/+2 | |
| 2022-09-30 | Merge pull request #1109 from d8ahazard/ModelLoader | AUTOMATIC1111 | -1385/+2145 | |
| Model Loader, Fixes | ||||
| 2022-09-30 | fix the sys not found error when importing sd_samplers that appeared after PR | AUTOMATIC | -10/+11 | |
| 2022-09-30 | force usage of cloned k-diffusion | C43H66N12O12S2 | -1/+2 | |
| 2022-09-30 | return shortest checkpoint title match | DepFA | -11/+1 | |
| 2022-09-30 | add get_closet_checkpoint_match | DepFA | -0/+15 | |
| 2022-09-29 | Fixes, cleanup. | d8ahazard | -17/+5 | |
| 2022-09-29 | Merge remote-tracking branch 'upstream/master' into ModelLoader | d8ahazard | -133/+483 | |
| 2022-09-29 | Holy $hit. | d8ahazard | -639/+1009 | |
| 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. | ||||
| 2022-09-29 | Save parameters as comments when saving as jpg | Justin Maier | -5/+14 | |
| 2022-09-29 | Save should use desired sample format fixes #1028 | Justin Maier | -1/+1 | |
| 2022-09-29 | fix for incorrect model weight loading for #814 | AUTOMATIC | -1/+14 | |
| 2022-09-29 | improve code quality | C43H66N12O12S2 | -9/+7 | |
| 2022-09-29 | add new samplers | C43H66N12O12S2 | -1/+10 | |
| 2022-09-29 | drop the print | Hanusz Leszek | -1/+0 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |