Text-to-Image
Diffusers
Safetensors
Ideogram4Pipeline
image-generation
diffusion
flow-matching
dit
ideogram
Instructions to use ideogram-ai/ideogram-4-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
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] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Image Filter Feedback
#9
by Someontwothree - opened
The following, rather generic fantasy prompt without characters, photorealism, gore, sex or whatever the built-in censorship is supposed to be "good" for, gets blocked, just as another example fyi:
"A classic oil painting of
a high-tech edged blade in a dynamic composition as the focus of attention, shown at a dramatic angle. The electro-mechanical claymore appears to be integrated with glowing circuits.
The bladed artifact is resting on a pedestal set in the mysterious heart of a misty, ancient jungle overgrown by thorny vines, wrapped around the scary trees.
The setting's nightmarish mood is defined by an intense glow."
