| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2023-05-10 | suggestions and fixes from the PR | AUTOMATIC | -2/+2 | |
| 2023-05-10 | ruff auto fixes | AUTOMATIC | -2/+2 | |
| 2023-05-10 | imports cleanup for ruff | AUTOMATIC | -2/+0 | |
| 2023-01-21 | extra networks UI | AUTOMATIC | -3/+2 | |
| rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight> | ||||
| 2023-01-10 | Variable dropout rate | aria1th | -2/+2 | |
| Implements variable dropout rate from #4549 Fixes hypernetwork multiplier being able to modified during training, also fixes user-errors by setting multiplier value to lower values for training. Changes function name to match torch.nn.module standard Fixes RNG reset issue when generating previews by restoring RNG state | ||||
| 2022-12-24 | implement train api | Vladimir Mandic | -27/+4 | |
| 2022-10-30 | We have duplicate linear now | AngelBottomless | -1/+1 | |
| 2022-10-29 | Re enable linear | AngelBottomless | -1/+1 | |
| 2022-10-27 | Disable unavailable or duplicate options | AngelBottomless | -1/+2 | |
| 2022-10-26 | Weight initialization and More activation func | AngelBottomless | -1/+3 | |
| add weight init add weight init option in create_hypernetwork fstringify hypernet info save weight initialization info for further debugging fill bias with zero for He/Xavier initialize LayerNorm with Normal fix loading weight_init | ||||
| 2022-10-22 | Merge branch 'master' of upstream | discus0434 | -2/+6 | |
| 2022-10-22 | add dropout | discus0434 | -5/+5 | |
| 2022-10-21 | Sanitize hypernet name input. | timntorres | -0/+3 | |
| 2022-10-21 | Merge branch 'master' into training-help-text | AUTOMATIC1111 | -2/+3 | |
| 2022-10-20 | Merge branch 'AUTOMATIC1111:master' into master | discus0434 | -1/+1 | |
| 2022-10-20 | allow float sizes for hypernet's layer_structure | AUTOMATIC | -1/+1 | |
| 2022-10-20 | update | discus0434 | -1/+2 | |
| 2022-10-20 | allow overwrite old hn | DepFA | -2/+3 | |
| 2022-10-19 | enable to write layer structure of hn himself | discus0434 | -0/+4 | |
| 2022-10-19 | layer options moves into create hnet ui | discus0434 | -2/+7 | |
| 2022-10-11 | reports that training with medvram is possible. | AUTOMATIC | -1/+1 | |
| 2022-10-11 | add an option to unload models during hypernetwork training to save VRAM | AUTOMATIC | -1/+3 | |
| 2022-10-11 | produce error when training with medvram/lowvram enabled | AUTOMATIC | -0/+2 | |
| 2022-10-11 | add option to select hypernetwork modules when creating | AUTOMATIC | -2/+2 | |
| 2022-10-11 | more renames | AUTOMATIC | -2/+2 | |
| 2022-10-11 | rename hypernetwork dir to hypernetworks to prevent clash with an old ↵ | AUTOMATIC | -0/+43 | |
| filename that people who use zip instead of git clone will have | ||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |