Age | Commit message (Collapse) | Author | Lines | |
---|---|---|---|---|
2022-10-31 | Fixed minor bug | Fampai | -0/+1 | |
when unloading vae during TI training, generating images after training will error out | ||||
2022-10-31 | Merge branch 'master' of ↵ | Fampai | -102/+247 | |
https://github.com/AUTOMATIC1111/stable-diffusion-webui into TI_optimizations | ||||
2022-10-31 | Added TI training optimizations | Fampai | -3/+16 | |
option to use xattention optimizations when training option to unload vae when training | ||||
2022-10-31 | Checkpoint cache by combination key of checkpoint and vae | Muhammad Rizqi Nur | -12/+23 | |
2022-10-31 | Fix typo from previous commit | Muhammad Rizqi Nur | -2/+2 | |
2022-10-31 | Extend extras image cache with upscale_first arg | DepFA | -1/+1 | |
2022-10-31 | prototype interrupt api | evshiron | -0/+6 | |
2022-10-31 | docs: add python doc (?) | Maiko Sinkyaet Tan | -0/+2 | |
not sure if this available... | ||||
2022-10-30 | Add callback to sd_samplers | DepFA | -0/+3 | |
2022-10-30 | add callback cleardown | DepFA | -1/+1 | |
2022-10-30 | Add callbacks and param objects | DepFA | -0/+27 | |
2022-10-31 | Added "--clip-models-path" switch to avoid using default "~/.cache/clip" and ↵ | mawr | -2/+3 | |
enable to run under unprivileged user without homedir | ||||
2022-10-30 | Merge branch 'AUTOMATIC1111:master' into adjust-ddim-uniform-steps | Martin Cairns | -111/+293 | |
2022-10-30 | Change VAE search order and thus priority | Muhammad Rizqi Nur | -2/+2 | |
2022-10-30 | Settings to select VAE | Muhammad Rizqi Nur | -24/+136 | |
2022-10-30 | feat: add app started callback | Maiko Tan | -0/+15 | |
2022-10-30 | add resrgan 8x, allow use 1x and up to 8x extra models, move BSRGAN model, ↵ | victorca25 | -6/+33 | |
add nearest | ||||
2022-10-30 | resolve conflicts | aria1th | -6/+38 | |
2022-10-30 | We have duplicate linear now | AngelBottomless | -1/+1 | |
2022-10-30 | add optimizer save option to shared.opts | AngelBottomless | -0/+1 | |
2022-10-30 | Include PLMS in adjust steps as it also can fail in the same way | Martin Cairns | -1/+1 | |
2022-10-30 | fix current image in progress api when parallel processing enabled | evshiron | -2/+11 | |
2022-10-30 | fix broken progress api by previous rework | evshiron | -0/+3 | |
2022-10-30 | Merge pull request #3928 from R-N/validate-before-load | AUTOMATIC1111 | -51/+107 | |
Optimize training a little | ||||
2022-10-30 | Merge pull request #3898 from R-N/lr-comma | AUTOMATIC1111 | -14/+21 | |
Allow trailing comma in learning rate | ||||
2022-10-30 | rework #3722 to not introduce duplicate code | AUTOMATIC | -33/+32 | |
2022-10-30 | Merge pull request #3722 from evshiron/feat/progress-api | AUTOMATIC1111 | -27/+108 | |
prototype progress api | ||||
2022-10-30 | shorten Hypernetwork strength in infotext and omit it when it's the default ↵ | AUTOMATIC | -2/+2 | |
value. | ||||
2022-10-30 | Merge pull request #3831 from timntorres/3825-save-hypernet-strength-to-info | AUTOMATIC1111 | -2/+7 | |
Save Hypernetwork strength to infotext. | ||||
2022-10-30 | fix broken hires fix | AUTOMATIC | -5/+2 | |
2022-10-30 | allow skip current image in progress api | evshiron | -2/+5 | |
2022-10-29 | Read hypernet strength from PNG info. | timntorres | -0/+1 | |
2022-10-29 | Merge commit 'e7254746bbfbff45099db44a8d4d25dd6181877d' into ↵ | timntorres | -49/+88 | |
3825-save-hypernet-strength-to-info | ||||
2022-10-30 | preview current image when opts.show_progress_every_n_steps is enabled | evshiron | -2/+7 | |
2022-10-30 | update progress response model | evshiron | -7/+7 | |
2022-10-30 | add description for state field | evshiron | -1/+1 | |
2022-10-30 | fix progress response model | evshiron | -34/+4 | |
2022-10-30 | Merge branch 'master' into feat/progress-api | evshiron | -10/+47 | |
2022-10-30 | Merge branch 'master' into feat/progress-api | evshiron | -484/+632 | |
2022-10-29 | Merge pull request #3934 from bamarillo/api-add-png-info-endpoint | AUTOMATIC1111 | -4/+17 | |
[API][Feature] Add png info endpoint | ||||
2022-10-29 | add postprocess call for scripts | AUTOMATIC | -6/+30 | |
2022-10-29 | Fix space | Bruno Seoane | -1/+1 | |
2022-10-29 | Add PNG Info endpoint | Bruno Seoane | -4/+17 | |
2022-10-30 | Fix dataset still being loaded even when training will be skipped | Muhammad Rizqi Nur | -2/+2 | |
2022-10-30 | Add missing info on hypernetwork/embedding model log | Muhammad Rizqi Nur | -23/+47 | |
Mentioned here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/1528#discussioncomment-3991513 Also group the saving into one | ||||
2022-10-30 | Revert "Add cleanup after training" | Muhammad Rizqi Nur | -200/+186 | |
This reverts commit 3ce2bfdf95bd5f26d0f6e250e67338ada91980d1. | ||||
2022-10-29 | Add adjust_steps_if_invalid to find next valid step for ddim uniform sampler | Martin Cairns | -13/+15 | |
2022-10-29 | Additional assert on dataset | Muhammad Rizqi Nur | -0/+2 | |
2022-10-29 | Add cleanup after training | Muhammad Rizqi Nur | -186/+200 | |
2022-10-29 | Add input validations before loading dataset for training | Muhammad Rizqi Nur | -28/+58 | |