# ideogram-oss/ideogram4

Ideogram 4: Open image model at the forefront of design

Repository: https://github.com/ideogram-oss/ideogram4
Canonical: https://ross.abutalabs.com/products/ideogram4
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-06-30T18:01:52+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 35, longevity 6
- inputs: {"age_days": 97, "days_push": 64, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2766, forks 286 (observed 2026-08-28T04:07:18.590508+00:00)

## What it is
Ideogram 4 is an open-weight text-to-image foundation model trained from scratch, with inference code and weights released in Python. It features structured JSON prompting, multilingual text rendering, bounding-box layout and color-palette controls, and native 2K resolution output.

## Use cases
- generate images from text prompts
- render legible text inside generated images
- control image layout with bounding boxes
- generate posters and design assets with specific color palettes
- run a state-of-the-art text-to-image model locally on GPU
- generate high-resolution 2k images

## When to avoid
- you need lightweight CPU-only image generation
- you only need image editing rather than text-to-image synthesis
- you lack a supported GPU for inference

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, image-processing, llm-inference
- domain: artificial-intelligence, image-processing, deep-learning, machine-learning
- platform: python
- tags: text-to-image, diffusion-model, open-weights, image-generation, typography, design, diffusers, gpu, linux

## Member repositories
- ideogram-oss/ideogram4 (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:18.590508+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:16:45.458267+00:00, confidence not recorded.
  - readme: https://github.com/ideogram-oss/ideogram4 (fetched 2026-08-28T04:07:18.590508+00:00, sha 8098c557d82e)
- Data as of 2026-08-30T08:39:29.467469+00:00.