Ideogram has released version 4.0 of its text-to-image model as an open-weight model, allowing users to run it on their own hardware and fine-tune it with their own data. The model includes native 2K resolution, transparent backgrounds, precise layout control via bounding boxes, and improved text rendering, which is particularly useful for logos and posters. Editable text and layers are set to be added in the future, according to the company.
The model is available in three quality tiers via Ideogram's hosted API, with pricing starting at $0.03 per image for the Turbo tier, $0.06 for the Default tier, and $0.10 for the Quality tier. It is also accessible on the web and across partner platforms, including Hugging Face, ComfyUI, and Replicate. According to the DesignArena leaderboard, Ideogram 4.0 ranks first among all open-weight models, with only closed models from OpenAI and Google scoring higher.
According to the source, Ideogram 4.0 easily outperforms Midjourney v8 in a benchmark test, lands roughly on par with Flux, but falls short of GPT-Image-2, Nano Banana Pro, or Luma Uni-1.1. The test mainly evaluates the model's ability to render abstract concepts unlikely to appear in the training data, such as a horse-riding astronaut. As always, the source recommends users conduct their own testing.
Source: thedecoder
