Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Update | Volpeon | 2023-03-06 | 1 | -5/+9 |
| | |||||
* | More flexible pipeline wrt init noise | Volpeon | 2023-03-04 | 1 | -13/+44 |
| | |||||
* | Added Perlin noise to training | Volpeon | 2023-03-04 | 1 | -2/+2 |
| | |||||
* | Update | Volpeon | 2023-03-04 | 1 | -9/+2 |
| | |||||
* | Pipeline: Perlin noise for init image | Volpeon | 2023-03-04 | 1 | -14/+9 |
| | |||||
* | Pipeline: Improved initial image generation | Volpeon | 2023-03-04 | 1 | -23/+26 |
| | |||||
* | Changed init noise algorithm | Volpeon | 2023-03-03 | 1 | -3/+11 |
| | |||||
* | Removed offset noise from training, added init offset to pipeline | Volpeon | 2023-03-03 | 1 | -56/+39 |
| | |||||
* | Update | Volpeon | 2023-02-13 | 1 | -32/+37 |
| | |||||
* | Integrate Self-Attention-Guided (SAG) Stable Diffusion in my custom pipeline | Volpeon | 2023-02-08 | 1 | -7/+162 |
| | |||||
* | Add Lora | Volpeon | 2023-02-07 | 1 | -2/+12 |
| | |||||
* | Restored functional trainer | Volpeon | 2023-01-15 | 1 | -8/+8 |
| | |||||
* | WIP: Modularization ("free(): invalid pointer" my ass) | Volpeon | 2023-01-14 | 1 | -1/+0 |
| | |||||
* | Removed PromptProcessor, modularized training loop | Volpeon | 2023-01-13 | 1 | -8/+12 |
| | |||||
* | Code deduplication | Volpeon | 2023-01-13 | 1 | -23/+9 |
| | |||||
* | Fixed aspect ratio bucketing; allow passing token IDs to pipeline | Volpeon | 2023-01-08 | 1 | -10/+30 |
| | |||||
* | Set default dimensions to 768; add config inheritance | Volpeon | 2022-12-26 | 1 | -4/+4 |
| | |||||
* | Fix training | Volpeon | 2022-12-20 | 1 | -9/+0 |
| | |||||
* | Upstream patches | Volpeon | 2022-12-19 | 1 | -5/+17 |
| | |||||
* | Add support for resume in Textual Inversion | Volpeon | 2022-12-13 | 1 | -19/+23 |
| | |||||
* | Dreambooth: Support loading Textual Inversion embeddings | Volpeon | 2022-12-12 | 1 | -5/+8 |
| | |||||
* | Support attention_mask of text encoder | Volpeon | 2022-12-10 | 1 | -4/+12 |
| | |||||
* | Update | Volpeon | 2022-12-04 | 2 | -16/+9 |
| | |||||
* | Update | Volpeon | 2022-12-01 | 1 | -16/+11 |
| | |||||
* | Update | Volpeon | 2022-11-30 | 1 | -1/+26 |
| | |||||
* | Update | Volpeon | 2022-11-14 | 1 | -6/+1 |
| | |||||
* | Refactoring | Volpeon | 2022-11-14 | 1 | -104/+214 |
| | |||||
* | Update | Volpeon | 2022-11-14 | 1 | -11/+22 |
| | |||||
* | Update | Volpeon | 2022-11-03 | 1 | -2/+34 |
| | |||||
* | Update | Volpeon | 2022-11-01 | 1 | -2/+3 |
| | |||||
* | New Euler_a scheduler | Volpeon | 2022-10-26 | 1 | -14/+13 |
| | |||||
* | Update | Volpeon | 2022-10-24 | 1 | -0/+3 |
| | |||||
* | Improved prompt handling | Volpeon | 2022-10-18 | 1 | -55/+17 |
| | |||||
* | Implemented extended prompt limit | Volpeon | 2022-10-17 | 1 | -41/+55 |
| | |||||
* | Upstream updates; better handling of textual embedding | Volpeon | 2022-10-17 | 1 | -1/+1 |
| | |||||
* | Update | Volpeon | 2022-10-15 | 1 | -6/+2 |
| | |||||
* | Removed aesthetic gradients; training improvements | Volpeon | 2022-10-14 | 1 | -46/+4 |
| | |||||
* | Added support for Aesthetic Gradients | Volpeon | 2022-10-13 | 1 | -3/+49 |
| | |||||
* | Various updates | Volpeon | 2022-10-12 | 1 | -6/+5 |
| | |||||
* | Update | Volpeon | 2022-10-08 | 1 | -2/+3 |
| | |||||
* | Update | Volpeon | 2022-10-06 | 1 | -30/+5 |
| | |||||
* | Small performance improvements | Volpeon | 2022-10-02 | 1 | -8/+10 |
| | |||||
* | Fix img2img | Volpeon | 2022-10-02 | 1 | -35/+36 |
| | |||||
* | More consistent euler_a | Volpeon | 2022-10-02 | 1 | -11/+6 |
| | |||||
* | WIP: img2img | Volpeon | 2022-10-02 | 1 | -16/+64 |
| | |||||
* | Fix seed, better progress bar, fix euler_a for batch size > 1 | Volpeon | 2022-10-01 | 1 | -2/+2 |
| | |||||
* | Made inference script interactive | Volpeon | 2022-10-01 | 1 | -166/+3 |
| | |||||
* | Added custom SD pipeline + euler_a scheduler | Volpeon | 2022-09-30 | 1 | -0/+457 |
| | |||||
* | Fix error when saving model | Volpeon | 2022-09-27 | 1 | -2/+2 |
| | |||||
* | Init | Volpeon | 2022-09-26 | 1 | -0/+13 |