summaryrefslogtreecommitdiffstats
Commit message (Expand)AuthorAgeFilesLines
...
* New loss weighting from arxiv.org:2204.00227Volpeon2023-03-181-2/+5
* Better SNR weightingVolpeon2023-03-181-3/+3
* Fixed snr weight calculationVolpeon2023-03-171-1/+4
* Fix loss=nanVolpeon2023-03-171-2/+2
* Test: https://arxiv.org/pdf/2303.09556.pdfVolpeon2023-03-173-39/+56
* UpdateVolpeon2023-03-075-27/+37
* UpdateVolpeon2023-03-063-25/+13
* More flexible pipeline wrt init noiseVolpeon2023-03-041-13/+44
* Added Perlin noise to trainingVolpeon2023-03-043-8/+28
* UpdateVolpeon2023-03-041-9/+2
* Pipeline: Perlin noise for init imageVolpeon2023-03-047-18/+70
* Pipeline: Improved initial image generationVolpeon2023-03-041-23/+26
* Changed init noise algorithmVolpeon2023-03-031-3/+11
* Removed offset noise from training, added init offset to pipelineVolpeon2023-03-034-68/+41
* Implemented different noise offsetVolpeon2023-03-036-28/+16
* Low freq noise with randomized strengthVolpeon2023-03-031-1/+8
* Better low freq noiseVolpeon2023-03-021-1/+1
* Changed low freq noiseVolpeon2023-03-011-23/+10
* UpdateVolpeon2023-03-0110-535/+39
* Fixed TI normalization orderVolpeon2023-02-213-15/+19
* FixVolpeon2023-02-211-6/+3
* Don't rely on Accelerate for gradient accumulationVolpeon2023-02-215-33/+32
* Embedding normalization: Ignore tensors with grad = 0Volpeon2023-02-217-45/+31
* UpdateVolpeon2023-02-185-15/+30
* Added Lion optimizerVolpeon2023-02-177-39/+592
* Inference script: Better scheduler configVolpeon2023-02-171-19/+37
* Back to xformersVolpeon2023-02-175-12/+14
* Remove xformers, switch to Pytorch NightlyVolpeon2023-02-1710-644/+27
* FixVolpeon2023-02-161-4/+2
* Integrated WIP UniPC schedulerVolpeon2023-02-166-14/+655
* UpdateVolpeon2023-02-153-1/+3
* Improved batch paddingVolpeon2023-02-151-29/+26
* Better batch fillingVolpeon2023-02-151-3/+6
* Better batch filling behaviorVolpeon2023-02-151-3/+7
* Dataset: Repeat data to fill batch to batch_sizeVolpeon2023-02-151-0/+3
* Made low-freq noise configurableVolpeon2023-02-141-6/+11
* Better noise generation during training: https://www.crosslabs.org/blog/diffu...Volpeon2023-02-131-0/+7
* UpdateVolpeon2023-02-1310-65/+73
* Integrate Self-Attention-Guided (SAG) Stable Diffusion in my custom pipelineVolpeon2023-02-084-17/+164
* Fixed Lora trainingVolpeon2023-02-084-37/+35
* Fix Lora memory usageVolpeon2023-02-075-11/+5
* Add LoraVolpeon2023-02-0710-93/+819
* Restored LR finderVolpeon2023-01-209-397/+111
* Move Accelerator preparation into strategyVolpeon2023-01-194-19/+51
* UpdateVolpeon2023-01-175-22/+25
* Optimized embedding normalizationVolpeon2023-01-171-5/+2
* Smaller emb decayVolpeon2023-01-171-1/+1
* FixVolpeon2023-01-171-4/+5
* FixVolpeon2023-01-171-1/+0
* Make embedding decay work like Adam decayVolpeon2023-01-172-21/+9