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
π The best model for consistent text rendering
I'm really impressed. The text is incredibly consistent, even when not specified in the prompt.
A fluffy golden retriever puppy chasing a bright red ball through a sunlit green meadow.
A cozy steaming mug of hot chocolate with marshmallows resting on a wooden table next to a stack of books.
A cute little green frog wearing a tiny yellow rain hat sitting peacefully on a lily pad.

Just read the prompting guide and that is all gone
https://huggingface.co/ideogram-ai/ideogram-4-fp8/discussions/5#6a208948d2802761c1c3a188
Okay, I figured it out now. The initial workflow had some issues that have been resolved. The ability to control the output with the node provided by Kijai is very helpful. This is a really good model with a high level of control.
