| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2022-10-21 | Refer to Hypernet's name, sensibly, by its name variable. | timntorres | -1/+1 | |
| 2022-10-21 | Match hypernet name with filename in all cases. | timntorres | -1/+7 | |
| 2022-10-21 | Sanitize hypernet name input. | timntorres | -0/+3 | |
| 2022-10-21 | Update image_embedding.py | DepFA | -2/+2 | |
| 2022-10-21 | Use opts in textual_inversion image_embedding.py for dynamic fonts | DepFA | -0/+1 | |
| 2022-10-21 | make aestetic embedding ciompatible with prompts longer than 75 tokens | AUTOMATIC | -1/+1 | |
| 2022-10-21 | do not load aesthetic clip model until it's needed | AUTOMATIC | -38/+88 | |
| add refresh button for aesthetic embeddings add aesthetic params to images' infotext | ||||
| 2022-10-21 | Merge branch 'ae' | AUTOMATIC | -21/+324 | |
| 2022-10-21 | Fix Hypernet infotext string split bug for PR #3283 | AUTOMATIC | -1/+1 | |
| 2022-10-21 | turns out LayerNorm also has weight and bias and needs to be pre-multiplied ↵ | AUTOMATIC | -2/+2 | |
| and trained for hypernets | ||||
| 2022-10-21 | Merge branch 'master' into training-help-text | AUTOMATIC1111 | -82/+552 | |
| 2022-10-21 | Remove redundant try/except. | timntorres | -5/+1 | |
| 2022-10-21 | Revise comments. | timntorres | -2/+2 | |
| 2022-10-21 | Do nothing if image file already exists. | timntorres | -1/+5 | |
| 2022-10-21 | Issue #2921-Give PNG info to Hypernet previews. | timntorres | -2/+7 | |
| 2022-10-21 | Allow datasets with only 1 image in TI | guaneec | -2/+2 | |
| 2022-10-21 | interrogate: Fix CLIP-interrogation on CPU | Patryk Wychowaniec | -3/+9 | |
| Currently, trying to perform CLIP interrogation on a CPU fails, saying: ``` RuntimeError: "slow_conv2d_cpu" not implemented for 'Half' ``` This merge request fixes this issue by detecting whether the target device is CPU and, if so, force-enabling `--no-half` and passing `device="cpu"` to `clip.load()` (which then does some extra tricks to ensure it works correctly on CPU). | ||||
| 2022-10-21 | Merge branch 'master' into master | AUTOMATIC1111 | -36/+493 | |
| 2022-10-21 | a more strict check for activation type and a more reasonable check for type ↵ | AUTOMATIC | -3/+9 | |
| of layer in hypernets | ||||
| 2022-10-21 | Merge pull request #3199 from discus0434/master | AUTOMATIC1111 | -11/+23 | |
| Add features to insert activation functions to hypernetworks | ||||
| 2022-10-21 | sort file list in alphabetical ordering in extras | winterspringsummer | -1/+1 | |
| 2022-10-21 | Fixed path issue while extras batch processing | winterspringsummer | -3/+3 | |
| 2022-10-21 | Added try except to extras batch from directory | winterspringsummer | -4/+7 | |
| 2022-10-21 | Fixed path issue while extras batch processing | winterspringsummer | -4/+8 | |
| 2022-10-21 | allow float sizes for hypernet's layer_structure | AUTOMATIC | -1/+1 | |
| 2022-10-21 | updated readme and some small stylistic changes to code | AUTOMATIC | -8/+9 | |
| 2022-10-20 | XY grid correctly re-assignes model when config changes | random_thoughtss | -3/+3 | |
| 2022-10-20 | Different approach to skip/interrupt with highres fix | Vladimir Repin | -1/+7 | |
| 2022-10-20 | Added PLMS hijack and made sure to always replace methods | random_thoughtss | -9/+157 | |
| 2022-10-20 | fix skip and interrupt for highres. fix option | Vladimir Repin | -3/+1 | |
| 2022-10-20 | Made dummy latents smaller. Minor code cleanups | random_thoughtss | -5/+8 | |
| 2022-10-21 | Revert "fix bugs and optimizations" | aria1th | -59/+46 | |
| This reverts commit 108be15500aac590b4e00420635d7b61fccfa530. | ||||
| 2022-10-21 | Merge branch 'AUTOMATIC1111:master' into Inspiron | 不会画画的中医不是好程序员 | -1/+1 | |
| 2022-10-21 | fix bugs and optimizations | AngelBottomless | -46/+59 | |
| 2022-10-20 | inspiration pull request | yfszzx | -5/+131 | |
| 2022-10-20 | only linear | AngelBottomless | -5/+5 | |
| 2022-10-20 | generalized some functions and option for ignoring first layer | AngelBottomless | -8/+15 | |
| 2022-10-20 | train: ui: added `Split image threshold` and `Split image overlap ratio` to ↵ | Milly | -7/+19 | |
| preprocess | ||||
| 2022-10-20 | train: fixed preprocess image ratio | Milly | -19/+35 | |
| 2022-10-20 | add linear as a act func (option for doin nothing) | discus0434 | -1/+1 | |
| 2022-10-20 | Merge branch 'AUTOMATIC1111:master' into master | discus0434 | -1/+1 | |
| 2022-10-20 | improve face detection a lot | captin411 | -37/+62 | |
| 2022-10-20 | Merge remote-tracking branch 'origin/master' | AUTOMATIC | -6/+3 | |
| 2022-10-20 | allow float sizes for hypernet's layer_structure | AUTOMATIC | -1/+1 | |
| 2022-10-19 | Fixed non-square highres fix generation | random_thoughtss | -3/+6 | |
| 2022-10-20 | do caption copy for both flips | DepFA | -1/+1 | |
| 2022-10-19 | face detection algo, configurability, reusability | captin411 | -136/+230 | |
| Try to move the crop in the direction of a face if it is present More internal configuration options for choosing weights of each of the algorithm's findings Move logic into its module | ||||
| 2022-10-20 | align ui.py imports with upstream | discus0434 | -19/+18 | |
| 2022-10-20 | update | discus0434 | -9/+11 | |
| 2022-10-20 | update | discus0434 | -31/+44 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |