Works with your own model
Takes the id of a custom model that has finished training and makes images with it.
Create a picture from a description
Train Ideogram on your photos, your style, your subject, your look, from a small set of reference images to images that feel consistently yours
Opens the image studio with Ideogram Generate ready to use. You can look around as a guest. Running it takes the Pro plan or higher.


What it makes
Create a picture from a description
Turns a written description into a picture.
What you need
You also make one choice about how it runs.
What you get
A new picture
Ideogram Generate makes images with a custom Ideogram model you have already trained. Examples are a model trained on your photos, your style or your subject. You write a short text description, called a prompt, and you get back an image.
You provide two things: the id of a custom model that has finished training, and the prompt. A model that is still training cannot be used. Three options are yours to change. Aspect Ratio has choices such as 16:9, 9:16, 3:2 and 2:3, and it starts at 1:1. Rendering Speed offers Turbo, Balanced or Quality, with Balanced as the starting choice. Expand Prompt lets Ideogram's MagicPrompt expand your text, and it starts switched on.
Ideogram Generate costs 300 credits per run. Ideogram Text to Image and Ideogram Transparent cost 300 credits too, but they need only a prompt. Ideogram Generate is the one that asks for a custom model id.
Same job: create a picture from a description. Compare before you choose.
A speed-tuned variant of Stable Diffusion XL that generates high-quality images in a handful of steps, trading a little fine detail for near-instant results - ideal for rapid concept exploration and draft iteration.
Alibaba's fast-inference Qwen Image variant, tuned for near-instant text-to-image generation without sacrificing prompt accuracy - built for rapid drafts and high-volume workflows.
Alibaba's Qwen Image model generates accurate, detailed visuals from text prompts with strong prompt comprehension, including legible in-image text and complex compositions.
A FLUX variant tuned by Krea for stylized, painterly image generation - strong for concept art and creative visuals that want more artistic flair than strict photorealism.
Takes the id of a custom model that has finished training and makes images with it.
You write a prompt and get back the generated image.
A custom model that is still training cannot be used.
Enter the id of your custom model. The model must have finished training.
Write a prompt. Change Aspect Ratio, Rendering Speed or Expand Prompt if you want to.
Run it for 300 credits and look at the image your custom model makes.
Make new images with a custom model that was trained on your own style.
Create new images of a subject that your custom model was trained on.
Quick answers to help you get the most out of Ideogram Generate in FunAI Studio.