Instructions to use spacepxl/Wan2.1-VAE-upscale2x with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use spacepxl/Wan2.1-VAE-upscale2x with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("spacepxl/Wan2.1-VAE-upscale2x", torch_dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Question About Using with Qwen
#11 opened 3 months ago
by
MikiePsyche
How is the real image training data constructed?
7
#10 opened 5 months ago
by
scf
does this work with video right now?
#8 opened 5 months ago
by
cloudinthesky
RuntimeError: Error(s) in loading state_dict for WanVideoVAE:
#7 opened 6 months ago
by
hydraofm0
Training Code Release?
#6 opened 7 months ago
by
Changlinn
Qwen-Image-Layered?
1
#5 opened 7 months ago
by
SassyDiffusion
Bad result
5
#4 opened 8 months ago
by
xuruipeng8641
Use for Direct Imae Upscaling?
1
#2 opened 9 months ago
by
tmanzz