How to use unsloth/ideogram-4-fp8 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("unsloth/ideogram-4-fp8", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
for some reason you guys have the model in your directory but it can't be found on the interface itself (the local deployment interface)downloaded separately, but the model is stuck on loading into memory (nothing is actually happening)
· Sign up or log in to comment
