Hugging Face's logo

codemichaeld
/
Wan_vae_upscale2x_fp8

Diffusers
Safetensors
fp8
pruned
diffusion
converted-by-gradio
fp8-e5m2
Model card Files
xet
 Community
How to use from the
Use from the
Diffusers library
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline

# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("codemichaeld/Wan_vae_upscale2x_fp8", dtype=torch.bfloat16, device_map="cuda")

prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]

FP8 Pruned Model (E5M2)

Converted from: https://huggingface.co/spacepxl/Wan2.1-VAE-upscale2x
File: Wan2.1_VAE_upscale2x_imageonly_real_v1.safetensors → Wan2.1_VAE_upscale2x_imageonly_real_v1-fp8-e5m2.safetensors

Quantization: FP8 (E5M2)
Converted on: 2025-12-01 06:49:45

Downloads last month
6
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support