import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("slzd/Z-Image-Base-0.36.0.dev0-fp32", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Z-Image Base v0.36.0.dev0 (FP32)
This repository provides a high-fidelity FP32 (Full Precision) mirror of the Z-Image base model.
- Source Commit: 1ac663b (Tongyi-MAI/Z-Image)
- Precision: Float32 (Full Precision)
Usage in Ostris AI Toolkit
To use this model for your training runs, replace the default model path in your configuration by:
Model Name/Path:
slzd/Z-Image-Base-0.36.0.dev0-fp32
Instead of:
Tongyi-MAI/Z-Image
- Downloads last month
- 13