Commit message (Expand) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | Fix TI embeddings init | Volpeon | 2023-03-26 | 1 | -1/+1 |
* | Improved TI embeddings | Volpeon | 2023-03-26 | 2 | -9/+24 |
* | Improved inverted tokens | Volpeon | 2023-03-26 | 5 | -34/+70 |
* | Fix training with guidance | Volpeon | 2023-03-25 | 2 | -6/+14 |
* | Update | Volpeon | 2023-03-25 | 8 | -987/+99 |
* | Update | Volpeon | 2023-03-24 | 4 | -9/+22 |
* | Fixed Lora training perf issue | Volpeon | 2023-03-24 | 2 | -9/+9 |
* | Lora fix: Save config JSON, too | Volpeon | 2023-03-24 | 1 | -0/+3 |
* | Refactoring, fixed Lora training | Volpeon | 2023-03-24 | 5 | -66/+104 |
* | Bring back Perlin offset noise | Volpeon | 2023-03-23 | 2 | -1/+21 |
* | Update | Volpeon | 2023-03-23 | 10 | -30/+29 |
* | Fix | Volpeon | 2023-03-22 | 3 | -6/+2 |
* | Log DAdam/DAdan d | Volpeon | 2023-03-21 | 4 | -6/+20 |
* | Added dadaptation | Volpeon | 2023-03-21 | 4 | -1/+85 |
* | Fixed SNR weighting, re-enabled xformers | Volpeon | 2023-03-21 | 5 | -50/+97 |
* | Restore min SNR | Volpeon | 2023-03-19 | 1 | -13/+12 |
* | New loss weighting from arxiv.org:2204.00227 | Volpeon | 2023-03-18 | 1 | -2/+5 |
* | Better SNR weighting | Volpeon | 2023-03-18 | 1 | -3/+3 |
* | Fixed snr weight calculation | Volpeon | 2023-03-17 | 1 | -1/+4 |
* | Fix loss=nan | Volpeon | 2023-03-17 | 1 | -2/+2 |
* | Test: https://arxiv.org/pdf/2303.09556.pdf | Volpeon | 2023-03-17 | 3 | -39/+56 |
* | Update | Volpeon | 2023-03-07 | 5 | -27/+37 |
* | Update | Volpeon | 2023-03-06 | 3 | -25/+13 |
* | More flexible pipeline wrt init noise | Volpeon | 2023-03-04 | 1 | -13/+44 |
* | Added Perlin noise to training | Volpeon | 2023-03-04 | 3 | -8/+28 |
* | Update | Volpeon | 2023-03-04 | 1 | -9/+2 |
* | Pipeline: Perlin noise for init image | Volpeon | 2023-03-04 | 7 | -18/+70 |
* | 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 | 4 | -68/+41 |
* | Implemented different noise offset | Volpeon | 2023-03-03 | 6 | -28/+16 |
* | Low freq noise with randomized strength | Volpeon | 2023-03-03 | 1 | -1/+8 |
* | Better low freq noise | Volpeon | 2023-03-02 | 1 | -1/+1 |
* | Changed low freq noise | Volpeon | 2023-03-01 | 1 | -23/+10 |
* | Update | Volpeon | 2023-03-01 | 10 | -535/+39 |
* | Fixed TI normalization order | Volpeon | 2023-02-21 | 3 | -15/+19 |
* | Fix | Volpeon | 2023-02-21 | 1 | -6/+3 |
* | Don't rely on Accelerate for gradient accumulation | Volpeon | 2023-02-21 | 5 | -33/+32 |
* | Embedding normalization: Ignore tensors with grad = 0 | Volpeon | 2023-02-21 | 7 | -45/+31 |
* | Update | Volpeon | 2023-02-18 | 5 | -15/+30 |
* | Added Lion optimizer | Volpeon | 2023-02-17 | 7 | -39/+592 |
* | Inference script: Better scheduler config | Volpeon | 2023-02-17 | 1 | -19/+37 |
* | Back to xformers | Volpeon | 2023-02-17 | 5 | -12/+14 |
* | Remove xformers, switch to Pytorch Nightly | Volpeon | 2023-02-17 | 10 | -644/+27 |
* | Fix | Volpeon | 2023-02-16 | 1 | -4/+2 |
* | Integrated WIP UniPC scheduler | Volpeon | 2023-02-16 | 6 | -14/+655 |
* | Update | Volpeon | 2023-02-15 | 3 | -1/+3 |
* | Improved batch padding | Volpeon | 2023-02-15 | 1 | -29/+26 |
* | Better batch filling | Volpeon | 2023-02-15 | 1 | -3/+6 |
* | Better batch filling behavior | Volpeon | 2023-02-15 | 1 | -3/+7 |