misc-models / README.md
kohya-ss's picture
Update README.md
ae38967 verified
|
raw
history blame
882 Bytes

sdxl-negprompt8-v1m.safetensors

Negative embeddings for sdxl. Num vectors per token = 8

stable-cascade-c-lora-hasui-v02.safetensors

Sample of LoRA for Stable Cascade Stage C.

Feb 22, 2024 Update: Fixed a bug that LoRA is not applied to some modules (to_q/k/v and to_out) in Attention.

This is an experimental model, so the format of the weights may change in the future.

  • a painting of an anthropomorphic penguin sitting in a cafe reading a book and having a coffee --w 1024 --h 1024 --d 1 sample1

  • a painting of japanese shrine in winter with snowfall --w 832 --h 1152 --d 1234 sample2

This model is trained with 169 images with captions. U-Net only, dim=4, conv_dim=4, alpha=1, lr=1e-3, 4 epochs, mixed precision bf16, 8bit AdamW, batch size 8, resolution 1024x1024 with aspect ratio bucketing. VRAM usage is approximately 22 GB.