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
Please either amend "Open Source" to "Open Weights" or comply with OSI requirements for "Open Source" models
Hello! Thank you for publishing the weights for Ideogram-4.
Please note that the Open Source Initiative distinguishes between "Open Weights" models (which publish only the model's weights/parameters) and "Open Source" models.
OSI provides criteria which must be met for a model to qualify as "Open Source":
https://opensource.org/ai/open-source-ai-definition
In short, those criteria include publishing the training software used to train the model and the training data information (either the dataset itself or a description of the training data sufficient to inform reproduction of a model of equivalent functionality), in addition to the model's weights.
The Open Source Initiative is the internationally recognized authority for defining what is considered "Open Source", including which licenses qualify as open source licenses. I am not affiliated with OSI.
If you could either meet the OSI criteria for using the "Open Source" label or amend your documentation to refer to Ideogram-4 as "Open Weights" instead of "Open Source", please, it would be appreciated by the open LLM community.
updated to open weights. Thank you!