import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("ivand-all3d/image-variation-experiments", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Image Variations Experiments
Check out the blog post.
Models
| Model | Description |
|---|---|
flux-image-variations |
A finetuned version of FLUX that accepts CLIP image embeddings |
pixart-custom-redux |
A custom adapter network that lets PixArt accept SigLip image embeddings, similar to Flux Redux |
pixart-flux-redux |
A finetuned version of PixArt that accepts T5 embeddings from the Flux Redux adapter network |
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ivand-all3d/image-variation-experiments
Base model
PixArt-alpha/PixArt-XL-2-512x512