Hugging Face's logo

Jersonm89
/
Avatar

Text-to-Image
Diffusers
StableDiffusionPipeline
stable-diffusion
Model card Files
xet
 Community
5
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("Jersonm89/Avatar", dtype=torch.bfloat16, device_map="cuda")

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

Model trained with images from James Cameron's Avatar movie. Draw avatar characters with facial features of the person indicated at the prompt

Sample images Will Smith: prompt= portrait Will Smith male, avatar style

output Samples v3 output Samples v3 output Samples v3

Sample images Johnny Depp: prompt= portrait Johnny Depp male, avatar style

output Samples v3 output Samples v3 output Samples v3

Downloads last month
17
Inference Providers NEW
Text-to-Image
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Spaces using Jersonm89/Avatar 2