import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("viettmab/dreamo", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]DreamO Fused Transformer v1.1
This repository contains the fused transformer weights for DreamO v1.1, a text-to-image diffusion model.
Model Details
- Model Type: Diffusion Transformer
- Version: 1.1
- File Format: SafeTensors
- Model Size: ~22GB
Usage
# Example usage code would go here
# This depends on the specific DreamO implementation
License
Please check the original DreamO repository for license information.
Citation
# Add appropriate citation if available
- Downloads last month
- 2