| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | Embed model merge metadata in .safetensors file | space-nuko | 2023-04-02 | 1 | -1/+10 |
| | | |||||
| * | sort hypernetworks and checkpoints by name | AUTOMATIC | 2023-03-28 | 1 | -1/+1 |
| | | |||||
| * | Merge pull request #8958 from MrCheeze/variations-model | AUTOMATIC1111 | 2023-03-28 | 1 | -0/+8 |
| |\ | | | | | Add support for the unclip (Variations) models, unclip-h and unclip-l | ||||
| | * | overwrite xformers in the unclip model config if not available | MrCheeze | 2023-03-26 | 1 | -0/+3 |
| | | | |||||
| | * | Add support for the Variations models (unclip-h and unclip-l) | MrCheeze | 2023-03-26 | 1 | -0/+5 |
| | | | |||||
| * | | Merge pull request #8780 from Brawlence/master | AUTOMATIC1111 | 2023-03-25 | 1 | -1/+21 |
| |\ \ | | | | | | | Unload and re-load checkpoint to VRAM on request (API & Manual) | ||||
| | * | | Unload checkpoints on Request | Φφ | 2023-03-21 | 1 | -1/+21 |
| | |/ | | | | | | | | | | | | | …to free VRAM. New Action buttons in the settings to manually free and reload checkpoints, essentially juggling models between RAM and VRAM. | ||||
| * / | fix variable typo | carat-johyun | 2023-03-23 | 1 | -2/+2 |
| |/ | |||||
| * | fix an error loading Lora with empty values in metadata | AUTOMATIC | 2023-03-14 | 1 | -1/+1 |
| | | |||||
| * | Add view metadata button for Lora cards. | AUTOMATIC | 2023-03-14 | 1 | -0/+24 |
| | | |||||
| * | when exists | w-e-w | 2023-02-19 | 1 | -1/+1 |
| | | |||||
| * | fix auto sd download issue | w-e-w | 2023-02-19 | 1 | -1/+7 |
| | | |||||
| * | Add ".vae.ckpt" to ext_blacklist | missionfloyd | 2023-02-16 | 1 | -1/+1 |
| | | |||||
| * | Download model if none are found | missionfloyd | 2023-02-15 | 1 | -1/+1 |
| | | |||||
| * | make it possible to load SD1 checkpoints without CLIP | AUTOMATIC | 2023-02-05 | 1 | -1/+5 |
| | | |||||
| * | fix issue with switching back to checkpoint that had its checksum calculated ↵ | AUTOMATIC | 2023-02-04 | 1 | -2/+3 |
| | | | | | during runtime mentioned in #7506 | ||||
| * | Merge pull request #7470 from ↵ | AUTOMATIC1111 | 2023-02-04 | 1 | -1/+1 |
| |\ | | | | | | | | | cbrownstein-lambda/update-error-message-no-checkpoint Update error message WRT missing checkpoint file | ||||
| | * | Update error message WRT missing checkpoint file | Cody Brownstein | 2023-02-01 | 1 | -1/+1 |
| | | | | | | | | | The Safetensors format is also supported. | ||||
| * | | add --no-hashing | AUTOMATIC | 2023-02-04 | 1 | -0/+3 |
| |/ | |||||
| * | support for searching subdirectory names for extra networks | AUTOMATIC | 2023-01-29 | 1 | -0/+1 |
| | | |||||
| * | fixed a bug where after switching to a checkpoint with unknown hash, you'd ↵ | AUTOMATIC | 2023-01-28 | 1 | -3/+1 |
| | | | | | | | get empty space instead of checkpoint name in UI fixed a bug where if you update a selected checkpoint on disk and then restart the program, a different checkpoint loads, but the name is shown for the the old one. | ||||
| * | add data-dir flag and set all user data directories based on it | Max Audron | 2023-01-27 | 1 | -3/+3 |
| | | |||||
| * | support detecting midas model | AUTOMATIC | 2023-01-27 | 1 | -5/+5 |
| | | | | | fix broken api for checkpoint list | ||||
| * | remove the need to place configs near models | AUTOMATIC | 2023-01-27 | 1 | -115/+113 |
| | | |||||
| * | Merge pull request #6510 from brkirch/unet16-upcast-precision | AUTOMATIC1111 | 2023-01-25 | 1 | -0/+10 |
| |\ | | | | | Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half | ||||
| | * | Add option for float32 sampling with float16 UNet | brkirch | 2023-01-25 | 1 | -0/+10 |
| | | | | | | | | | 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(). | ||||
| * | | Add instruct-pix2pix hijack | Kyle | 2023-01-25 | 1 | -1/+11 |
| |/ | | | | | | Allows loading instruct-pix2pix models via same method as inpainting models in sd_models.py and sd_hijack_ip2p.py Adds ddpm_edit.py necessary for instruct-pix2pix | ||||
| * | bring back short hashes to sd checkpoint selection | AUTOMATIC | 2023-01-19 | 1 | -4/+11 |
| | | |||||
| * | fix bug with "Ignore selected VAE for..." option completely disabling VAE ↵ | AUTOMATIC | 2023-01-14 | 1 | -3/+3 |
| | | | | | | | election rework VAE resolving code to be more simple | ||||
| * | load hashes from cache for checkpoints that have them | AUTOMATIC | 2023-01-14 | 1 | -3/+6 |
| | | | | | add checkpoint hash to footer | ||||
| * | update key to use with checkpoints' sha256 in cache | AUTOMATIC | 2023-01-14 | 1 | -1/+1 |
| | | |||||
| * | change hypernets to use sha256 hashes | AUTOMATIC | 2023-01-14 | 1 | -1/+1 |
| | | |||||
| * | change hash to sha256 | AUTOMATIC | 2023-01-14 | 1 | -42/+74 |
| | | |||||
| * | fix for an error caused by skipping initialization, for realsies this time: ↵ | AUTOMATIC | 2023-01-11 | 1 | -0/+1 |
| | | | | | TypeError: expected str, bytes or os.PathLike object, not NoneType | ||||
| * | possible fix for fallback for fast model creation from config, attempt 2 | AUTOMATIC | 2023-01-11 | 1 | -0/+1 |
| | | |||||
| * | possible fix for fallback for fast model creation from config | AUTOMATIC | 2023-01-11 | 1 | -0/+3 |
| | | |||||
| * | add support for transformers==4.25.1 | AUTOMATIC | 2023-01-10 | 1 | -2/+6 |
| | | | | | add fallback for when quick model creation fails | ||||
| * | add more stuff to ignore when creating model from config | AUTOMATIC | 2023-01-10 | 1 | -4/+28 |
| | | | | | prevent .vae.safetensors files from being listed as stable diffusion models | ||||
| * | disable torch weight initialization and CLIP downloading/reading checkpoint ↵ | AUTOMATIC | 2023-01-10 | 1 | -2/+3 |
| | | | | | to speedup creating sd model from config | ||||
| * | allow model load if previous model failed | Vladimir Mandic | 2023-01-09 | 1 | -5/+10 |
| | | |||||
| * | use commandline-supplied cuda device name instead of cuda:0 for safetensors ↵ | AUTOMATIC | 2023-01-04 | 1 | -1/+1 |
| | | | | | PR that doesn't fix anything | ||||
| * | Merge remote-tracking branch 'Narsil/fix_safetensors_load_speed' | AUTOMATIC | 2023-01-04 | 1 | -1/+4 |
| |\ | |||||
| | * | Attempting to solve slow loads for `safetensors`. | Nicolas Patry | 2022-12-27 | 1 | -1/+4 |
| | | | | | | | | | Fixes #5893 | ||||
| * | | fix broken inpainting model | AUTOMATIC | 2023-01-04 | 1 | -3/+0 |
| | | | |||||
| * | | find configs for models at runtime rather than when starting | AUTOMATIC | 2023-01-04 | 1 | -13/+18 |
| | | | |||||
| * | | helpful error message when trying to load 2.0 without config | AUTOMATIC | 2023-01-04 | 1 | -8/+18 |
| | | | | | | | | | failing to load model weights from settings won't break generation for currently loaded model anymore | ||||
| * | | call script callbacks for reloaded model after loading embeddings | AUTOMATIC | 2023-01-03 | 1 | -2/+2 |
| | | | |||||
| * | | fix the issue with training on SD2.0 | AUTOMATIC | 2023-01-01 | 1 | -0/+2 |
| | | | |||||
| * | | validate textual inversion embeddings | Vladimir Mandic | 2022-12-31 | 1 | -0/+3 |
| |/ | |||||
| * | fix F541 f-string without any placeholders | Yuval Aboulafia | 2022-12-24 | 1 | -4/+4 |
| | | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |