import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("zenlm/zen3-image", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]zen3-image
Flagship text-to-image generation (20B MMDiT).
Repackaged from Qwen/Qwen-Image (apache-2.0, Alibaba Qwen). Not trained from scratch — a permissively-licensed redistribution for the OSS-clean Zen model line.
License
apache-2.0. Upstream: Qwen/Qwen-Image by Alibaba Qwen. Upstream LICENSE/NOTICE retained in-repo.
- Downloads last month
- 49
Model tree for zenlm/zen3-image
Base model
Qwen/Qwen-Image