How to use ideogram-ai/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("ideogram-ai/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]
Without Controlnet functionality it is useless for me as I need exact poses (canny, lineart, pyracanny, etc.) plus joycaption type enhanced descriptions to keep almost identical images bar the person (via a character Lora).
· Sign up or log in to comment
