| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2022-10-30 | Merge pull request #3928 from R-N/validate-before-load | AUTOMATIC1111 | -26/+43 | |
| Optimize training a little | ||||
| 2022-10-30 | Fix dataset still being loaded even when training will be skipped | Muhammad Rizqi Nur | -1/+1 | |
| 2022-10-30 | Add missing info on hypernetwork/embedding model log | Muhammad Rizqi Nur | -10/+21 | |
| Mentioned here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/1528#discussioncomment-3991513 Also group the saving into one | ||||
| 2022-10-30 | Revert "Add cleanup after training" | Muhammad Rizqi Nur | -105/+96 | |
| This reverts commit 3ce2bfdf95bd5f26d0f6e250e67338ada91980d1. | ||||
| 2022-10-29 | Add cleanup after training | Muhammad Rizqi Nur | -96/+105 | |
| 2022-10-29 | Add input validations before loading dataset for training | Muhammad Rizqi Nur | -16/+22 | |
| 2022-10-29 | Merge branch 'AUTOMATIC1111:master' into 3825-save-hypernet-strength-to-info | timntorres | -5/+8 | |
| 2022-10-29 | Merge pull request #3858 from R-N/log-csv | AUTOMATIC1111 | -5/+7 | |
| Fix log off by 1 #3847 | ||||
| 2022-10-28 | Fix log off by 1 | Muhammad Rizqi Nur | -5/+7 | |
| 2022-10-28 | Always ignore "None.pt" in the hypernet directory. | timntorres | -2/+5 | |
| 2022-10-28 | Add missing support for linear activation in hypernetwork | benkyoujouzu | -0/+1 | |
| 2022-10-26 | patch bug (SeverianVoid's comment on 5245c7a) | timntorres | -1/+1 | |
| 2022-10-26 | remove duplicate keys and lowercase | AngelBottomless | -1/+1 | |
| 2022-10-26 | Weight initialization and More activation func | AngelBottomless | -9/+38 | |
| 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 | ||||
| 2022-10-24 | check length for variance | AngelBottomless | -2/+10 | |
| 2022-10-24 | convert deque -> list | AngelBottomless | -1/+1 | |
| I don't feel this being efficient | ||||
| 2022-10-24 | statistics for pbar | AngelBottomless | -2/+10 | |
| 2022-10-24 | cleanup some code | AngelBottomless | -11/+3 | |
| 2022-10-24 | Hypernetworks - fix KeyError in statistics caching | AngelBottomless | -2/+2 | |
| Statistics logging has changed to {filename : list[losses]}, so it has to use loss_info[key].pop() | ||||
| 2022-10-23 | Update hypernetwork.py | DepFA | -4/+7 | |
| 2022-10-22 | Allow tracking real-time loss | AngelBottomless | -1/+1 | |
| Someone had 6000 images in their dataset, and it was shown as 0, which was confusing. This will allow tracking real time dataset-average loss for registered objects. | ||||
| 2022-10-22 | Update hypernetwork.py | AngelBottomless | -11/+44 | |
| 2022-10-22 | small fix | discus0434 | -4/+3 | |
| 2022-10-22 | Merge branch 'AUTOMATIC1111:master' into master | discus0434 | -0/+11 | |
| 2022-10-22 | small fix | discus0434 | -7/+5 | |
| 2022-10-22 | add an option to avoid dying relu | discus0434 | -6/+6 | |
| 2022-10-22 | added a guard for hypernet training that will stop early if weights are ↵ | AUTOMATIC | -0/+11 | |
| getting no gradients | ||||
| 2022-10-22 | Merge branch 'master' of upstream | discus0434 | -8/+18 | |
| 2022-10-22 | add dropout | discus0434 | -26/+42 | |
| 2022-10-21 | Remove unused variable. | timntorres | -1/+0 | |
| 2022-10-21 | Match hypernet name with filename in all cases. | timntorres | -1/+7 | |
| 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 | -40/+56 | |
| 2022-10-21 | Revise comments. | timntorres | -1/+1 | |
| 2022-10-21 | Issue #2921-Give PNG info to Hypernet previews. | timntorres | -2/+7 | |
| 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 | Revert "fix bugs and optimizations" | aria1th | -59/+46 | |
| This reverts commit 108be15500aac590b4e00420635d7b61fccfa530. | ||||
| 2022-10-21 | fix bugs and optimizations | AngelBottomless | -46/+59 | |
| 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 | update | discus0434 | -10/+19 | |
| 2022-10-20 | change html output | DepFA | -1/+1 | |
| 2022-10-19 | fix for #3086 failing to load any previous hypernet | discus0434 | -32/+28 | |
| 2022-10-19 | layer options moves into create hnet ui | discus0434 | -32/+32 | |
| 2022-10-19 | Merge branch 'master' into master | discus0434 | -3/+2 | |
| 2022-10-19 | Use training width/height when training hypernetworks. | Silent | -2/+2 | |
| 2022-10-19 | update | discus0434 | -2/+2 | |
| 2022-10-19 | update | discus0434 | -6/+8 | |
| 2022-10-19 | add options to custom hypernetwork layer structure | discus0434 | -21/+67 | |
| 2022-10-15 | check NaN for hypernetwork tuning | AngelBottomless | -4/+6 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |