import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("lavinal712/sd-vae-ft-mse-midjourneyv6", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]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
- 23
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support