Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Merge branch 'master' into racecond_fix | AUTOMATIC1111 | 2022-12-03 | 1 | -148/+186 |
|\ | |||||
| * | Use devices.autocast instead of torch.autocast | brkirch | 2022-11-30 | 1 | -1/+1 |
| | | |||||
| * | Merge remote-tracking branch 'flamelaw/master' | AUTOMATIC | 2022-11-27 | 1 | -141/+182 |
| |\ | |||||
| | * | set TI AdamW default weight decay to 0 | flamelaw | 2022-11-26 | 1 | -1/+1 |
| | | | |||||
| | * | small fixes | flamelaw | 2022-11-22 | 1 | -1/+1 |
| | | | |||||
| | * | fix pin_memory with different latent sampling method | flamelaw | 2022-11-21 | 1 | -6/+1 |
| | | | |||||
| | * | Gradient accumulation, autocast fix, new latent sampling method, etc | flamelaw | 2022-11-20 | 1 | -137/+183 |
| | | | |||||
| * | | Add support Stable Diffusion 2.0 | AUTOMATIC | 2022-11-26 | 1 | -4/+3 |
| |/ | |||||
| * | 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/+5 |
|/ | | | | | set_current_image can attempt to use the VAE when it is unloaded to the CPU while training | ||||
* | Fixed minor bug | Fampai | 2022-10-31 | 1 | -0/+1 |
| | | | | | when unloading vae during TI training, generating images after training will error out | ||||
* | Merge branch 'master' of ↵ | Fampai | 2022-10-31 | 1 | -25/+62 |
|\ | | | | | | | https://github.com/AUTOMATIC1111/stable-diffusion-webui into TI_optimizations | ||||
| * | Fix dataset still being loaded even when training will be skipped | Muhammad Rizqi Nur | 2022-10-29 | 1 | -1/+1 |
| | | |||||
| * | Add missing info on hypernetwork/embedding model log | Muhammad Rizqi Nur | 2022-10-29 | 1 | -13/+26 |
| | | | | | | | | | | | | Mentioned here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/1528#discussioncomment-3991513 Also group the saving into one | ||||
| * | Revert "Add cleanup after training" | Muhammad Rizqi Nur | 2022-10-29 | 1 | -95/+90 |
| | | | | | | | | This reverts commit 3ce2bfdf95bd5f26d0f6e250e67338ada91980d1. | ||||
| * | Add cleanup after training | Muhammad Rizqi Nur | 2022-10-29 | 1 | -90/+95 |
| | | |||||
| * | Add input validations before loading dataset for training | Muhammad Rizqi Nur | 2022-10-29 | 1 | -12/+36 |
| | | |||||
* | | Added TI training optimizations | Fampai | 2022-10-31 | 1 | -0/+9 |
|/ | | | | | option to use xattention optimizations when training option to unload vae when training | ||||
* | Fix log off by 1 | Muhammad Rizqi Nur | 2022-10-28 | 1 | -12/+12 |
| | |||||
* | typo: cmd_opts.embedding_dir to cmd_opts.embeddings_dir | DepFA | 2022-10-26 | 1 | -1/+1 |
| | |||||
* | Implement PR #3625 but for embeddings. | timntorres | 2022-10-26 | 1 | -1/+1 |
| | |||||
* | Implement PR #3309 but for embeddings. | timntorres | 2022-10-26 | 1 | -1/+8 |
| | |||||
* | Implement PR #3189 but for embeddings. | timntorres | 2022-10-26 | 1 | -5/+5 |
| | |||||
* | enable creating embedding with --medvram | AUTOMATIC | 2022-10-26 | 1 | -0/+3 |
| | |||||
* | Merge branch 'ae' | AUTOMATIC | 2022-10-21 | 1 | -0/+1 |
|\ | |||||
| * | Merge branch 'master' into test_resolve_conflicts | MalumaDev | 2022-10-18 | 1 | -0/+1 |
| |\ | |||||
| * \ | Merge branch 'master' into test_resolve_conflicts | MalumaDev | 2022-10-16 | 1 | -0/+1 |
| |\ \ | |||||
| * \ \ | Merge branch 'master' into test_resolve_conflicts | MalumaDev | 2022-10-15 | 1 | -4/+13 |
| |\ \ \ | |||||
| * \ \ \ | Merge branch 'master' into test_resolve_conflicts | MalumaDev | 2022-10-15 | 1 | -25/+54 |
| |\ \ \ \ | |||||
| * | | | | | init | MalumaDev | 2022-10-14 | 1 | -10/+25 |
| | | | | | | |||||
* | | | | | | allow overwrite old embedding | DepFA | 2022-10-19 | 1 | -2/+3 |
| |_|_|_|/ |/| | | | | |||||
* | | | | | print list of embeddings on reload | DepFA | 2022-10-17 | 1 | -0/+1 |
| |_|_|/ |/| | | | |||||
* | | | | do not reload embeddings from disk when doing textual inversion | AUTOMATIC | 2022-10-16 | 1 | -0/+1 |
| |_|/ |/| | | |||||
* | | | Change vector size footer label | DepFA | 2022-10-15 | 1 | -1/+1 |
| | | | |||||
* | | | generalise to popular lossless formats | DepFA | 2022-10-15 | 1 | -6/+2 |
| | | | |||||
* | | | add webp for embed load | DepFA | 2022-10-15 | 1 | -0/+4 |
| | | | |||||
* | | | only save 1 image per embedding | DepFA | 2022-10-15 | 1 | -1/+4 |
| | | | |||||
* | | | add vector size to embed text | DepFA | 2022-10-15 | 1 | -1/+7 |
| |/ |/| | |||||
* | | add option to use batch size for training | AUTOMATIC | 2022-10-15 | 1 | -9/+8 |
| | | |||||
* | | remove duplicate code for log loss, add step, make it read from options ↵ | AUTOMATIC | 2022-10-14 | 1 | -14/+30 |
| | | | | | | | | rather than gradio input | ||||
* | | Merge remote-tracking branch 'Melanpan/master' | AUTOMATIC | 2022-10-14 | 1 | -0/+16 |
|\ \ | |||||
| * | | Add learn_rate to csv and removed a left-over debug statement | Melan | 2022-10-13 | 1 | -2/+3 |
| | | | |||||
| * | | Save a csv containing the loss while training | Melan | 2022-10-12 | 1 | -1/+16 |
| |/ | |||||
* / | add option to read generation params for learning previews from txt2img | AUTOMATIC | 2022-10-14 | 1 | -7/+18 |
|/ | |||||
* | train: change filename processing to be more simple and configurable | AUTOMATIC | 2022-10-12 | 1 | -22/+13 |
| | | | | | | train: make it possible to make text files with prompts train: rework scheduler so that there's less repeating code in textual inversion and hypernets train: move epochs setting to options | ||||
* | Merge pull request #2037 from AUTOMATIC1111/embed-embeddings-in-images | AUTOMATIC1111 | 2022-10-12 | 1 | -2/+44 |
|\ | | | | | Add option to store TI embeddings in png chunks, and load from same. | ||||
| * | formatting | DepFA | 2022-10-12 | 1 | -11/+11 |
| | | |||||
| * | spacing | DepFA | 2022-10-11 | 1 | -1/+1 |
| | | |||||
| * | update imports | DepFA | 2022-10-11 | 1 | -0/+3 |
| | | |||||
| * | correct conflict resolution typo | DepFA | 2022-10-11 | 1 | -1/+1 |
| | |