import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("maedtb/zimage-f32-diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]The ZImage Base model in F32 format.
This is the originally uploaded weights from the ZImage huggingface repo, before they were deleted and replaced with the down-scaled BF16 version for release--this is not the BF16 release converted to F32.
This model is in the original diffusers format.
- Downloads last month
- -
Model tree for maedtb/zimage-f32-diffusers
Base model
Tongyi-MAI/Z-Image