| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2023-06-20 | PNG info support at img2img batch | Ferdinand Weynschenk | -5/+40 | |
| 2023-06-19 | Add use_main_prompt parameter to use proper metadata for batch run grids or ↵ | stablegeniusdiffuser | -6/+7 | |
| individual images | ||||
| 2023-06-19 | fix: adding elem_id for img2img resize to and resize by tabs | George Gu | -2/+2 | |
| 2023-06-18 | update the description of --add-stop-rout | w-e-w | -1/+1 | |
| 2023-06-16 | :bug: Allow Script to have metaclass | huchenlei | -1/+2 | |
| 2023-06-16 | fix very slow loading speed of .safetensors files | dhwz | -2/+6 | |
| 2023-06-16 | Update call method | XiaoMeng Mai | -5/+9 | |
| 2023-06-15 | Add an opt-in infotext user name setting | Jared Deckard | -1/+2 | |
| 2023-06-15 | Add a user pattern to the filename generator | Jared Deckard | -0/+1 | |
| 2023-06-15 | Update code style | XiaoMeng Mai | -3/+1 | |
| 2023-06-15 | Add github mirror for the download extension | XiaoMeng Mai | -4/+20 | |
| 2023-06-14 | Note the Gradio user in the Exif data | Jared Deckard | -3/+11 | |
| 2023-06-15 | git clone show progress | w-e-w | -2/+2 | |
| 2023-06-14 | Fix gradio special args in the call queue | Jared Deckard | -0/+3 | |
| 2023-06-14 | terminate -> stop | w-e-w | -2/+2 | |
| 2023-06-14 | response 501 if not a able to restart | w-e-w | -0/+1 | |
| 2023-06-14 | rename routes | w-e-w | -5/+5 | |
| 2023-06-13 | textual_inversion/logging.py: clean up duplicate key from sets (and sort ↵ | Aarni Koskela | -4/+44 | |
| them) (Ruff B033) | ||||
| 2023-06-13 | Upscaler.load_model: don't return None, just use exceptions | Aarni Koskela | -26/+21 | |
| 2023-06-13 | Add TODO comments to sus model loads | Aarni Koskela | -0/+1 | |
| 2023-06-13 | Fix up `if "http" in ...:` to be more sensible startswiths | Aarni Koskela | -4/+4 | |
| 2023-06-13 | Move `load_file_from_url` to modelloader | Aarni Koskela | -8/+29 | |
| 2023-06-13 | Use os.makedirs(..., exist_ok=True) | Aarni Koskela | -15/+6 | |
| 2023-06-12 | move _stop route to api | w-e-w | -2/+9 | |
| 2023-06-12 | update model checkpoint switch code | Su Wei | -5/+4 | |
| 2023-06-10 | quit restart | w-e-w | -1/+10 | |
| 2023-06-09 | fixed typos | arch-fan | -2/+2 | |
| 2023-06-09 | linter | AUTOMATIC | -1/+1 | |
| 2023-06-09 | Merge pull request #11087 from AUTOMATIC1111/persistent_conds_cache | AUTOMATIC1111 | -10/+17 | |
| persistent conds cache | ||||
| 2023-06-09 | Split mask blur into X and Y components | Splendide Imaginarius | -4/+17 | |
| Prequisite to fixing Outpainting MK2 mask blur bug. | ||||
| 2023-06-09 | add model exists status check to modeuls/api/api.py , /sdapi/v1/options [POST] | Su Wei | -1/+6 | |
| 2023-06-08 | persistent conds cache | w-e-w | -10/+17 | |
| Update shared.py | ||||
| 2023-06-07 | Merge pull request #11058 from AUTOMATIC1111/api-wiki | AUTOMATIC1111 | -1/+1 | |
| link footer API to Wiki when API is not active | ||||
| 2023-06-07 | Merge pull request #11066 from aljungberg/patch-1 | AUTOMATIC1111 | -1/+1 | |
| Fix upcast attention dtype error. | ||||
| 2023-06-06 | Fix upcast attention dtype error. | Alexander Ljungberg | -1/+1 | |
| 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 | link footer API to Wiki when API is not active | w-e-w | -1/+1 | |
| 2023-06-06 | Merge pull request #11047 from ↵ | AUTOMATIC1111 | -9/+12 | |
| 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 | -9/+12 | |
| print error and continue | ||||
| 2023-06-05 | Remove a bunch of unused/vestigial code | Aarni Koskela | -89/+0 | |
| As found by Vulture and some eyes | ||||
| 2023-06-05 | Merge pull request #11037 from AUTOMATIC1111/restart-autolaunch | AUTOMATIC1111 | -0/+1 | |
| fix rework-disable-autolaunch for new restart method | ||||
| 2023-06-06 | SD_WEBUI_RESTARTING | w-e-w | -1/+1 | |
| 2023-06-05 | Merge pull request #11043 from akx/restart-envvar | AUTOMATIC1111 | -12/+31 | |
| 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 | -12/+31 | |
| 2023-06-06 | rework-disable-autolaunch | w-e-w | -0/+1 | |
| 2023-06-05 | revert the message to how it was | AUTOMATIC | -1/+3 | |
| 2023-06-05 | Merge pull request #10956 from akx/len | AUTOMATIC1111 | -38/+37 | |
| Simplify a bunch of `len(x) > 0`/`len(x) == 0` style expressions | ||||
| 2023-06-04 | Add endpoint to get latent_upscale_modes for hires fix | ramyma | -0/+12 | |
| 2023-06-04 | prevent calculating cons for second pass of hires fix when they are the same ↵ | AUTOMATIC | -7/+13 | |
| as for the first pass | ||||
| 2023-06-04 | fix for conds of second hires fox pass being calculated using first pass's ↵ | AUTOMATIC | -3/+36 | |
| networks, and add an option to revert to old behavior | ||||
| 2023-06-04 | Merge pull request #10997 from ↵ | AUTOMATIC1111 | -15/+16 | |
| AUTOMATIC1111/fix-conds-caching-with-extra-network fix conds caching with extra network | ||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |