Finetune repo: lavinal712/AutoencoderKL
Dataset: CortexLM/midjourney-v6
Fine-tuning modules: decoder and post_quant_conv
Input:
Reconstruction:
| metrics on ImageNet | rFID | PSNR | SSIM | LPIPS |
|---|---|---|---|---|
| sd-vae-ft-mse | 0.692 | 26.910 | 0.772 | 0.130 |
| finetuned (ours) | 1.638 | 27.046 | 0.785 | 0.126 |
- Downloads last month
- 15
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for lavinal712/sd-vae-ft-mse-midjourneyv6
Base model
stabilityai/sd-vae-ft-mse