| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | sort hypernetworks and checkpoints by name | AUTOMATIC | 2023-03-28 | 1 | -1/+1 |
| | | |||||
| * | Merge branch 'master' into weighted-learning | AUTOMATIC1111 | 2023-02-19 | 1 | -2/+2 |
| |\ | |||||
| | * | Support for hypernetworks with --upcast-sampling | brkirch | 2023-02-06 | 1 | -2/+2 |
| | | | |||||
| * | | Add ability to choose using weighted loss or not | Shondoit | 2023-02-15 | 1 | -4/+9 |
| | | | |||||
| * | | Call weighted_forward during training | Shondoit | 2023-02-15 | 1 | -1/+2 |
| |/ | |||||
| * | add --no-hashing | AUTOMATIC | 2023-02-04 | 1 | -1/+1 |
| | | |||||
| * | enable compact view for train tab | AUTOMATIC | 2023-01-21 | 1 | -0/+2 |
| | | | | | prevent previews from ruining hypernetwork training | ||||
| * | extra networks UI | AUTOMATIC | 2023-01-21 | 1 | -32/+75 |
| | | | | | rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight> | ||||
| * | add option to show/hide warnings | AUTOMATIC | 2023-01-18 | 1 | -1/+6 |
| | | | | | | removed hiding warnings from LDSR fixed/reworked few places that produced warnings | ||||
| * | Fix tensorboard related functions | aria1th | 2023-01-15 | 1 | -7/+6 |
| | | |||||
| * | Fix loss_dict problem | aria1th | 2023-01-15 | 1 | -1/+3 |
| | | |||||
| * | fix missing 'mean loss' for tensorboard integration | AngelBottomless | 2023-01-15 | 1 | -1/+1 |
| | | |||||
| * | big rework of progressbar/preview system to allow multiple users to prompts ↵ | AUTOMATIC | 2023-01-15 | 1 | -3/+3 |
| | | | | | at the same time and do not get previews of each other | ||||
| * | change hypernets to use sha256 hashes | AUTOMATIC | 2023-01-14 | 1 | -17/+23 |
| | | |||||
| * | change hash to sha256 | AUTOMATIC | 2023-01-14 | 1 | -2/+2 |
| | | |||||
| * | Merge branch 'master' into tensorboard | AUTOMATIC1111 | 2023-01-13 | 1 | -143/+484 |
| |\ | |||||
| | * | set descriptions | Vladimir Mandic | 2023-01-11 | 1 | -1/+3 |
| | | | |||||
| | * | Variable dropout rate | aria1th | 2023-01-10 | 1 | -25/+76 |
| | | | | | | | | | | | | | | | | | | | | | 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 | ||||
| | * | make a dropdown for prompt template selection | AUTOMATIC | 2023-01-09 | 1 | -2/+5 |
| | | | |||||
| | * | Move batchsize check | dan | 2023-01-07 | 1 | -1/+1 |
| | | | |||||
| | * | Add checkbox for variable training dims | dan | 2023-01-07 | 1 | -1/+1 |
| | | | |||||
| | * | rework saving training params to file #6372 | AUTOMATIC | 2023-01-06 | 1 | -21/+7 |
| | | | |||||
| | * | Include model in log file. Exclude directory. | timntorres | 2023-01-05 | 1 | -18/+10 |
| | | | |||||
| | * | Clean up ti, add same behavior to hypernetwork. | timntorres | 2023-01-05 | 1 | -1/+30 |
| | | | |||||
| | * | Merge branch 'master' into gradient-clipping | AUTOMATIC1111 | 2023-01-04 | 1 | -139/+202 |
| | |\ | |||||
| | | * | add job info to modules | Vladimir Mandic | 2023-01-03 | 1 | -0/+1 |
| | | | | |||||
| | | * | Merge pull request #5992 from yuvalabou/F541 | AUTOMATIC1111 | 2022-12-25 | 1 | -2/+2 |
| | | |\ | | | | | | | | | Fix F541: f-string without any placeholders | ||||
| | | | * | fix F541 f-string without any placeholders | Yuval Aboulafia | 2022-12-24 | 1 | -2/+2 |
| | | | | | |||||
| | | * | | implement train api | Vladimir Mandic | 2022-12-24 | 1 | -0/+26 |
| | | |/ | |||||
| | | * | Merge branch 'master' into racecond_fix | AUTOMATIC1111 | 2022-12-03 | 1 | -130/+216 |
| | | |\ | |||||
| | | | * | Use devices.autocast instead of torch.autocast | brkirch | 2022-11-30 | 1 | -1/+1 |
| | | | | | |||||
| | | | * | last_layer_dropout default to False | flamelaw | 2022-11-23 | 1 | -1/+1 |
| | | | | | |||||
| | | | * | fix dropout, implement train/eval mode | flamelaw | 2022-11-23 | 1 | -6/+18 |
| | | | | | |||||
| | | | * | small fixes | flamelaw | 2022-11-22 | 1 | -3/+3 |
| | | | | | |||||
| | | | * | fix pin_memory with different latent sampling method | flamelaw | 2022-11-21 | 1 | -1/+4 |
| | | | | | |||||
| | | | * | Gradient accumulation, autocast fix, new latent sampling method, etc | flamelaw | 2022-11-20 | 1 | -123/+146 |
| | | | | | |||||
| | | | * | change StableDiffusionProcessing to internally use sampler name instead of ↵ | AUTOMATIC | 2022-11-19 | 1 | -2/+2 |
| | | | | | | | | | | | | | | | | | sampler index | ||||
| | | * | | Fixes race condition in training when VAE is unloaded | Fampai | 2022-11-04 | 1 | -0/+4 |
| | | | | | | | | | | | | | | | | | | | | | set_current_image can attempt to use the VAE when it is unloaded to the CPU while training | ||||
| | * | | | Merge branch 'master' into gradient-clipping | Muhammad Rizqi Nur | 2022-11-07 | 1 | -6/+53 |
| | |\ \ \ | | | |/ | | |/| | |||||
| | | * | | rework the code to not use the walrus operator because colab's 3.7 does not ↵ | AUTOMATIC | 2022-11-05 | 1 | -2/+5 |
| | | | | | | | | | | | | | | | | | support it | ||||
| | | * | | Merge pull request #4273 from Omegastick/ordered_hypernetworks | AUTOMATIC1111 | 2022-11-05 | 1 | -1/+1 |
| | | |\ \ | | | | | | | | | | | Sort hypernetworks list | ||||
| | | | * | | Sort straight out of the glob | Isaac Poulton | 2022-11-04 | 1 | -2/+2 |
| | | | | | | |||||
| | | | * | | Sort hypernetworks | Isaac Poulton | 2022-11-04 | 1 | -1/+1 |
| | | | |/ | |||||
| | | * | | only save if option is enabled | aria1th | 2022-11-04 | 1 | -1/+1 |
| | | | | | |||||
| | | * | | split before declaring file name | aria1th | 2022-11-04 | 1 | -1/+1 |
| | | | | | |||||
| | | * | | apply | aria1th | 2022-11-04 | 1 | -5/+49 |
| | | |/ | |||||
| | * | | Simplify grad clip | Muhammad Rizqi Nur | 2022-11-05 | 1 | -9/+7 |
| | | | | |||||
| | * | | Merge branch 'master' into gradient-clipping | Muhammad Rizqi Nur | 2022-11-04 | 1 | -12/+24 |
| | |\| | |||||
| | | * | Merge branch 'master' into hn-activation | AUTOMATIC1111 | 2022-11-04 | 1 | -33/+56 |
| | | |\ | |||||
| | | * | | Revert unresolved changes in Bias initialization | AngelBottomless | 2022-10-27 | 1 | -1/+1 |
| | | | | | | | | | | | | | it should be zeros_ or parameterized in future properly. | ||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |