Text-to-Image
Diffusers
Safetensors
English
FluxPipeline
Flux
fp8
float8_e4m3fn
anime
figure
PVC
PVC anime figure
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("John6666/xe-figure-flux-01-fp8-flux", torch_dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Original model is here.
Use prompt words like:
An anime pvc figure of <...>
This model created by XEZ.
Notice
This is an experimental conversion in Spaces using a homebrew script. serverless Inference API does not currently support torch float8_e4m3fn, so it does not work. I have not been able to confirm if the conversion is working properly. Please consider this as a test run only.
- Downloads last month
- -