Instructions to use RamonGuthrie/z_image_base-nvfp8-mixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use RamonGuthrie/z_image_base-nvfp8-mixed with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("RamonGuthrie/z_image_base-nvfp8-mixed", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Z-Image-Base-NVFP8-mixed
I created this version to get close as possible to the fp32 in quality and prompt understanding, but with better speed and people with lower hardware can use and run. I wanted the head room to build more complex workflows, use more models and LLMs without running out of vram or OOM!
Download model
Download them in the Files & versions tab.
- Downloads last month
- 217
Model tree for RamonGuthrie/z_image_base-nvfp8-mixed
Base model
Tongyi-MAI/Z-Image