Age | Commit message (Collapse) | Author | |
---|---|---|---|
2023-06-14 | response 501 if not a able to restart | w-e-w | |
2023-06-14 | update workflow kill test server | w-e-w | |
2023-06-14 | rename routes | w-e-w | |
2023-06-12 | remove fastapi.Response | w-e-w | |
2023-06-12 | move _stop route to api | w-e-w | |
2023-06-10 | quit restart | w-e-w | |
2023-06-09 | add changelog for 1.4.0 | AUTOMATIC | |
2023-06-09 | linter | AUTOMATIC | |
2023-06-09 | Merge pull request #11092 from AUTOMATIC1111/Generate-Forever-during-generation | AUTOMATIC1111 | |
Allow activation of Generate Forever during generation | |||
2023-06-09 | Merge pull request #11087 from AUTOMATIC1111/persistent_conds_cache | AUTOMATIC1111 | |
persistent conds cache | |||
2023-06-09 | Merge pull request #11123 from akx/dont-die-on-bad-symlink-lora | AUTOMATIC1111 | |
Don't die when a LoRA is a broken symlink | |||
2023-06-09 | Merge pull request #10295 from Splendide-Imaginarius/mk2-blur-mask | AUTOMATIC1111 | |
Split mask blur into X and Y components, patch Outpainting MK2 accordingly | |||
2023-06-09 | Merge pull request #11048 from DGdev91/force_python1_navi_renoir | AUTOMATIC1111 | |
Forcing Torch Version to 1.13.1 for RX 5000 series GPUs | |||
2023-06-09 | Don't die when a LoRA is a broken symlink | Aarni Koskela | |
Fixes #11098 | |||
2023-06-09 | Split Outpainting MK2 mask blur into X and Y components | Splendide Imaginarius | |
Fixes unexpected noise in non-outpainted borders when using MK2 script. | |||
2023-06-09 | Split mask blur into X and Y components | Splendide Imaginarius | |
Prequisite to fixing Outpainting MK2 mask blur bug. | |||
2023-06-08 | Generate Forever during generation | w-e-w | |
Generate Forever during generation | |||
2023-06-08 | persistent conds cache | w-e-w | |
Update shared.py | |||
2023-06-07 | Merge pull request #11058 from AUTOMATIC1111/api-wiki | AUTOMATIC1111 | |
link footer API to Wiki when API is not active | |||
2023-06-07 | Merge pull request #11066 from aljungberg/patch-1 | AUTOMATIC1111 | |
Fix upcast attention dtype error. | |||
2023-06-06 | Fix upcast attention dtype error. | Alexander Ljungberg | |
Without this fix, enabling the "Upcast cross attention layer to float32" option while also using `--opt-sdp-attention` breaks generation with an error: ``` File "/ext3/automatic1111/stable-diffusion-webui/modules/sd_hijack_optimizations.py", line 612, in sdp_attnblock_forward out = torch.nn.functional.scaled_dot_product_attention(q, k, v, dropout_p=0.0, is_causal=False) RuntimeError: Expected query, key, and value to have the same dtype, but got query.dtype: float key.dtype: float and value.dtype: c10::Half instead. ``` The fix is to make sure to upcast the value tensor too. | |||
2023-06-06 | Skip force pyton and pytorch ver if TORCH_COMMAND already set | DGdev91 | |
2023-06-06 | link footer API to Wiki when API is not active | w-e-w | |
2023-06-06 | Write "RX 5000 Series" instead of "Navi" in err | DGdev91 | |
2023-06-06 | Check python version for Navi 1 only | DGdev91 | |
2023-06-06 | Force python1 for Navi1 only, use python_cmd for python | DGdev91 | |
2023-06-06 | Fix error in webui.sh | DGdev91 | |
2023-06-06 | Forcing Torch Version to 1.13.1 for Navi and Renoir GPUs | DGdev91 | |
2023-06-06 | Merge pull request #11047 from ↵ | AUTOMATIC1111 | |
AUTOMATIC1111/parse_generation_parameters_with_error handles exception when parsing generation parameters from png info | |||
2023-06-06 | print error and continue | w-e-w | |
print error and continue | |||
2023-06-05 | Merge pull request #11037 from AUTOMATIC1111/restart-autolaunch | AUTOMATIC1111 | |
fix rework-disable-autolaunch for new restart method | |||
2023-06-06 | SD_WEBUI_RESTARTING | w-e-w | |
2023-06-06 | restore old disable --autolaunch | w-e-w | |
2023-06-05 | Merge pull request #11031 from akx/zoom-and-pan-namespace | AUTOMATIC1111 | |
Zoom and pan: namespace & simplify | |||
2023-06-05 | Merge pull request #11043 from akx/restart-envvar | AUTOMATIC1111 | |
Restart: only do restart if running via the wrapper script | |||
2023-06-05 | Restart: only do restart if running via the wrapper script | Aarni Koskela | |
2023-06-06 | rework-disable-autolaunch | w-e-w | |
2023-06-05 | revert the message to how it was | AUTOMATIC | |
2023-06-05 | Merge pull request #10956 from akx/len | AUTOMATIC1111 | |
Simplify a bunch of `len(x) > 0`/`len(x) == 0` style expressions | |||
2023-06-05 | Zoom and Pan: simplify waitForOpts | Aarni Koskela | |
2023-06-05 | Zoom and Pan: use for instead of forEach | Aarni Koskela | |
2023-06-05 | Zoom and Pan: simplify getElements (it's not actually async) | Aarni Koskela | |
2023-06-05 | Zoom and Pan: use elementIDs from closure scope | Aarni Koskela | |
2023-06-05 | Zoom and Pan: move helpers into its namespace to avoid littering global scope | Aarni Koskela | |
2023-06-05 | Merge branch 'master' into dev | AUTOMATIC | |
2023-06-05 | Merge branch 'release_candidate' | AUTOMATIC | |
2023-06-04 | Merge pull request #11013 from ramyma/get_latent_upscale_modes_api | AUTOMATIC1111 | |
Get latent upscale modes API endpoint | |||
2023-06-04 | Add endpoint to get latent_upscale_modes for hires fix | ramyma | |
2023-06-04 | prevent calculating cons for second pass of hires fix when they are the same ↵ | AUTOMATIC | |
as for the first pass | |||
2023-06-04 | fix for conds of second hires fox pass being calculated using first pass's ↵ | AUTOMATIC | |
networks, and add an option to revert to old behavior |