Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | suggestions and fixes from the PR | AUTOMATIC | 2023-05-10 | 1 | -2/+2 |
| | |||||
* | ruff auto fixes | AUTOMATIC | 2023-05-10 | 1 | -2/+2 |
| | |||||
* | imports cleanup for ruff | AUTOMATIC | 2023-05-10 | 1 | -2/+0 |
| | |||||
* | extra networks UI | AUTOMATIC | 2023-01-21 | 1 | -3/+2 |
| | | | | rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight> | ||||
* | Variable dropout rate | aria1th | 2023-01-10 | 1 | -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 | ||||
* | implement train api | Vladimir Mandic | 2022-12-24 | 1 | -27/+4 |
| | |||||
* | We have duplicate linear now | AngelBottomless | 2022-10-30 | 1 | -1/+1 |
| | |||||
* | Re enable linear | AngelBottomless | 2022-10-28 | 1 | -1/+1 |
| | |||||
* | Disable unavailable or duplicate options | AngelBottomless | 2022-10-27 | 1 | -1/+2 |
| | |||||
* | Weight initialization and More activation func | AngelBottomless | 2022-10-26 | 1 | -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 | ||||
* | Merge branch 'master' of upstream | discus0434 | 2022-10-22 | 1 | -2/+6 |
|\ | |||||
| * | Sanitize hypernet name input. | timntorres | 2022-10-21 | 1 | -0/+3 |
| | | |||||
| * | Merge branch 'master' into training-help-text | AUTOMATIC1111 | 2022-10-21 | 1 | -2/+3 |
| |\ | |||||
| * | | allow overwrite old hn | DepFA | 2022-10-19 | 1 | -2/+3 |
| | | | |||||
* | | | add dropout | discus0434 | 2022-10-22 | 1 | -5/+5 |
| |/ |/| | |||||
* | | Merge branch 'AUTOMATIC1111:master' into master | discus0434 | 2022-10-20 | 1 | -1/+1 |
|\ \ | |||||
| * | | allow float sizes for hypernet's layer_structure | AUTOMATIC | 2022-10-20 | 1 | -1/+1 |
| |/ | |||||
* / | update | discus0434 | 2022-10-20 | 1 | -1/+2 |
|/ | |||||
* | enable to write layer structure of hn himself | discus0434 | 2022-10-19 | 1 | -0/+4 |
| | |||||
* | layer options moves into create hnet ui | discus0434 | 2022-10-19 | 1 | -2/+7 |
| | |||||
* | reports that training with medvram is possible. | AUTOMATIC | 2022-10-11 | 1 | -1/+1 |
| | |||||
* | add an option to unload models during hypernetwork training to save VRAM | AUTOMATIC | 2022-10-11 | 1 | -1/+3 |
| | |||||
* | produce error when training with medvram/lowvram enabled | AUTOMATIC | 2022-10-11 | 1 | -0/+2 |
| | |||||
* | add option to select hypernetwork modules when creating | AUTOMATIC | 2022-10-11 | 1 | -2/+2 |
| | |||||
* | more renames | AUTOMATIC | 2022-10-11 | 1 | -2/+2 |
| | |||||
* | rename hypernetwork dir to hypernetworks to prevent clash with an old ↵ | AUTOMATIC | 2022-10-11 | 1 | -0/+43 |
filename that people who use zip instead of git clone will have |