Login Sign up
Ideogram 4.0

Open image model at the forefront of design.

Built for design: open weights, multilingual text, precise layout control, editable elements, and realistic 2K images.

Future of design

The open approach

The future of generative AI is open source.

Chromium outran every closed browser engine, PyTorch is the dominant ML framework, and most of the internet runs on open source software. Over the past year, proprietary image models have set a new standard on text rendering, prompt adherence, and photorealism, while open weight models have fallen behind.

Today, we are releasing Ideogram 4.0 as a state-of-the-art open weight image model for developers and enterprises to build with us. The weights are yours to download, fine-tune, and run on your own hardware. Commercial deployments come with a license that matches your scale. We believe openness drives innovation, and we invite the research community to innovate with us on the forefront of visual intelligence.

DesignArena benchmark chart showing Ideogram 4.0 highlighted among leading image models.
World's first benchmark for real-world design with 4M+ creators and counting. Made by @arcada_labs

Model training

Teaching the model to read structure before recreating it.

A picture is worth a thousand words. Ideogram 4.0 was trained with a describe-to-structure-to-recreate loop: first reading scenes, backgrounds, text, and objects as structured data, then learning to rebuild images from that representation.

Input image Reference
A modern living room with a mustard yellow wall, gray sofa, cat painting, side tables, and floor lamp.
Structured description
High level description

A modern living room with an orange wall, featuring a gray sofa, a geometric gold side table, and a large colorful abstract painting of a cat's face hanging above the sofa.

Composition

Background

A solid mustard yellow wall serves as the backdrop for the entire scene. The floor is dark wood or laminate. A light-colored woven rug with vertical stripes lies on the floor in front of the furniture.

Cat painting obj

A large square canvas painting of a stylized cat's face, mounted on the yellow wall above the sofa. The artwork is divided into geometric sections with bold colors: blue and yellow for the left eye area, orange and red for the right eye area, and black for the ears and nose. The cat has large yellow eyes with black pupils and simple whiskers. The style is abstract and modern.

Gray sofa obj

A gray upholstered sofa with tufted back cushions sits centrally in front of the wall. It is adorned with two dark blue throw pillows on either end and one small rectangular pillow with a geometric pattern in shades of brown, white, and gray in the center.

Gold side table obj

A small round side table made of gold-toned metal wire in a hexagonal frame design sits to the right of the sofa. On top of it rests a dark ceramic mug on a saucer and an open book.

Floor lamp obj

A tall black tripod floor lamp stands to the right of the sofa. It has an adjustable arm ending in a silver-colored dome-shaped lamp head.

Left side table obj

To the left of the sofa is a small wooden side table with two shelves. On top sits a tall white vase containing green leaves from a plant. Below it are several stacked books.

                    {
  "high_level_description": "A modern living room with an orange wall, featuring a gray sofa, a geometric gold side table, and a large colorful abstract painting of a cat's face hanging above the sofa.",
  "compositional_deconstruction": {
    "background": "A solid mustard yellow wall serves as the backdrop for the entire scene. The floor is dark wood or laminate. A light-colored woven rug with vertical stripes lies on the floor in front of the furniture.",
    "elements": [
      {
        "type": "obj",
        "desc": "A large square canvas painting of a stylized cat's face, mounted on the yellow wall above the sofa. The artwork is divided into geometric sections with bold colors: blue and yellow for the left eye area, orange and red for the right eye area, and black for the ears and nose. The cat has large yellow eyes with black pupils and simple whiskers. The style is abstract and modern."
      },
      {
        "type": "obj",
        "desc": "A gray upholstered sofa with tufted back cushions sits centrally in front of the wall. It is adorned with two dark blue throw pillows on either end and one small rectangular pillow with a geometric pattern in shades of brown, white, and gray in the center."
      },
      {
        "type": "obj",
        "desc": "A small round side table made of gold-toned metal wire in a hexagonal frame design sits to the right of the sofa. On top of it rests a dark ceramic mug on a saucer and an open book."
      },
      {
        "type": "obj",
        "desc": "A tall black tripod floor lamp stands to the right of the sofa. It has an adjustable arm ending in a silver-colored dome-shaped lamp head."
      },
      {
        "type": "obj",
        "desc": "To the left of the sofa is a small wooden side table with two shelves. On top sits a tall white vase containing green leaves from a plant. Below it are several stacked books."
      }
    ]
  }
}
                  
Recreated image Output
A recreated modern living room with a mustard yellow wall, gray sofa, cat painting, side tables, and floor lamp.

Composition control

Design with every element in the right place.

We trained Ideogram 4.0 with bounding boxes coupled to plain-language descriptions, teaching the model where each object, text region, and layout element belongs before it paints the final image. That structure lets the model learn tighter composition in dramatically less training time, while giving creators fine-grained control over dense, compelling layouts.

Hover a layer to trace the same bounding box from the prompt plan to the generated poster.

Portrait prompt

12
                  {
  "high_level_description": "A minimalist movie poster for the film 'Flow' by Gints Zilbalodis, featuring a stylized black cat floating on its back against a textured cream-colored background. The title is written in a hand-drawn, textured font above the cat, surrounded by various film festival logos and promotional text.",
  "compositional_deconstruction": {
    "background": "The background is a solid, light beige or parchment-colored paper texture with a subtle grainy finish. A thin white border surrounds the entire image. A small black back arrow icon is located in the top-left corner.",
    "elements": [
      {
        "bbox": [
          18,
          725,
          319,
          936
        ],
        "desc": "Small credit block in the top right corner. Centered alignment, uppercase serif font in a dark grey or black color.",
        "text": "DREAM WELL STUDIO PRESENTS\nIN CO-PRODUCTION WITH\nSACREBLEU PRODUCTIONS\nAND TAKE FIVE\nA FILM BY GINTS ZILBALODIS \"FLOW\"\nWRITTEN BY GINTS ZILBALODIS MATISS KAZA\nDIRECTOR OF ANIMATION LÉO SILLY PÉLISSIER\nSOUND DESIGN BY GURWAL COÏC-GALLAS\nMUSIC BY GINTS ZILBALODIS\nRIHARDS ZALUPE\nRE-RECORDING MIXER PHILIPPE CHARBONNEL\nART DIRECTION, CINEMATOGRAPHY AND EDITING BY\nGINTS ZILBALODIS\nPRODUCED BY\nMATISS KAZA GINTS ZILBALODIS\nRON DYENS GREGORY ZALCMAN\nDIRECTED BY GINTS ZILBALODIS IN CO-PRODUCTION WITH\nARTE FRANCE CINEMA RTBF\n(BELGIAN TV) WITH THE SUPPORT OF CANAL+ CINÉ+\nWITH THE INVOLVEMENT OF ARTE FRANCE\nWITH THE SUPPORT OF EURIMAGES\nWITH THE SUPPORT OF THE PROVENCE ALPES-CÔTE\nD'AZUR REGION IN PARTNERSHIP WITH CNC\nWITH THE SUPPORT OF NATIONAL CENTER FOR\nCINEMA AND ANIMATED IMAGE\nIN ASSOCIATION WITH INDEFILMS 12 / LA BANQUE\nPOSTALE IMAGE 17 / CINEMAGE 1\nWITH THE SUPPORT OF THE TAX SHELTER OF THE\nBELGIAN FEDERAL GOVERNMENT\nWITH THE SUPPORT OF THE NATIONAL FILM CENTRE\nOF LATVIA LATVIAN STATE CULTURE\nCAPITAL FUND\nAND LATVIAN TELEVISION\nINTERNATIONAL SALES CHARADES",
        "type": "text"
      },
      {
        "bbox": [
          88,
          171,
          131,
          482
        ],
        "desc": "Small pull quote at the top center. Uppercase serif font, dark grey. The attribution INDIWIRE is in a slightly bolder font.",
        "text": "“BRIMMING WITH SENTIMENT BUT\nNOT SENTIMENTALITY”\nINDIWIRE",
        "type": "text"
      },
      {
        "bbox": [
          156,
          183,
          185,
          470
        ],
        "desc": "Small pull quote below the first one, centered. Uppercase serif font, dark grey. The attribution THE TELEGRAPH is in a slightly bolder font.",
        "text": "“OPEN, ALIVE, ELEMENTAL”\nTHE TELEGRAPH",
        "type": "text"
      },
      {
        "bbox": [
          267,
          26,
          313,
          140
        ],
        "desc": "Small film festival laurel and text on the left side. Black, serif font, uppercase.",
        "text": "FESTIVAL DE CANNES\nUN CERTAIN REGARD\n2024 OFFICIAL SELECTION",
        "type": "text"
      },
      {
        "bbox": [
          330,
          751,
          351,
          915
        ],
        "desc": "A horizontal row of five small production company logos in various colors including red and black, located below the main credit block.",
        "type": "obj"
      },
      {
        "bbox": [
          334,
          46,
          387,
          120
        ],
        "desc": "Small TIFF festival logo and text on the left side. Black, mix of lowercase and uppercase serif/sans-serif fonts.",
        "text": "OFFICIAL SELECTION\ntiff\nTORONTO INTERNATIONAL\nFILM FESTIVAL 2024",
        "type": "text"
      },
      {
        "bbox": [
          403,
          28,
          436,
          139
        ],
        "desc": "Small Annecy festival laurel and text on the left side. Black, serif font, uppercase.",
        "text": "OFFICIAL SELECTION\nANNECY\nCOMPETITION",
        "type": "text"
      },
      {
        "bbox": [
          426,
          212,
          484,
          432
        ],
        "desc": "Medium-sized text centered above the title. Bold, uppercase sans-serif font in black.",
        "text": "A FILM BY\nGINTS\nZILBALODIS",
        "type": "text"
      },
      {
        "bbox": [
          503,
          102,
          608,
          497
        ],
        "desc": "Large title centered in the frame. Hand-drawn, chunky, charcoal-textured black script font.",
        "text": "Flow",
        "type": "text"
      },
      {
        "bbox": [
          531,
          746,
          638,
          919
        ],
        "desc": "Medium-sized award text on the right side next to a silhouette of a Golden Globe trophy. Bold, uppercase sans-serif font in black.",
        "text": "GOLDEN\nGLOBE®\nWINNER\nBEST ANIMATED\nFEATURE FILM",
        "type": "text"
      },
      {
        "bbox": [
          531,
          876,
          612,
          919
        ],
        "desc": "Silhouette of a Golden Globe award trophy, small to medium size, solid black, located on the right side of the frame.",
        "type": "obj"
      },
      {
        "bbox": [
          611,
          4,
          956,
          967
        ],
        "desc": "A large, stylized black cat silhouette at the bottom of the frame. The cat is floating or falling on its back with four legs and tail pointing upward. It has a grainy charcoal-like texture, soft textured edges, and simple white circular eyes.",
        "type": "obj"
      }
    ]
  }
}
                
Bounding boxes
Credit block
Indiwire quote
Telegraph quote
Cannes laurel
Production logos
TIFF laurel
Annecy laurel
Director credit
Flow title
Golden Globe text
Globe trophy
Floating cat
A minimalist poster for Flow with a hand-drawn black title, film credits, festival laurels, a Golden Globe award note, and a black cat floating on a cream paper background.
Credit block
Indiwire quote
Telegraph quote
Cannes laurel
Production logos
TIFF laurel
Annecy laurel
Director credit
Flow title
Golden Globe text
Globe trophy
Floating cat

For designers

Generations come out as editable files, not flat frames.

Production design rarely ends at a single pixel layer. Headlines change before launch and cutouts drop onto new backdrops. Ideogram already ships these workflows as separate tools, and the next 4.0 release brings them native to the model itself.

Shipping today

Background removal already returns transparent output.

The Background Remover produces a clean alpha cutout from any generation, so the result drops onto a new backdrop without manual masking or Photoshop cleanup.

Shipping today

Layerize already extracts editable text.

Headlines, body copy, and graphic elements come back as separate editable layers, so the typography stays revisable after the model is done.

Coming to 4.0

The next release of 4.0 returns alpha channels and editable text layers directly from inference. No second pass, no masking step. The model's output is the editable file your team can hand to production.

Why this matters

Choose the open model designed for the work your team actually ships.

Open-weight image models are no longer scarce. The decision an enterprise faces is which one to standardize on, and which capabilities will hold up against the next two years of brand work and platform shifts.

  1. Brand work is the lane it was built for.

    Ideogram has led on text rendering since launch, and 4.0 adds bounding-box layout control. Headlines stay readable, packaging copy says the right words, and logos land where the brief asked for them.

  2. It converges on your house style, not on generic taste.

    Open weights and a commercial license let your team fine-tune on style guides, product photography, and historical campaigns until the model defaults to your look instead of fighting it.

  3. It runs where your CIO needs it to run.

    Deploy on your hardware, behind your firewall, in the region your residency rules name. Inference cost scales with the compute you provision, not with how many images marketing ships next quarter.

Enterprise

Frontier visual intelligence built for your brand.

Ideogram 4.0 is built for enterprises across every sector. It ships with open weights, a commercial license, and the customization options enterprises need. Run it on your hardware, train it on your data, and keep your output behind your firewall.

Learn more
Advertising example 1
Advertising example 2
Advertising example 3
Advertising example 4
Advertising example 5
Advertising example 6

API

Use Ideogram 4.0 commercially through the hosted API.

The fastest way to integrate Ideogram 4.0 into your product is through the API. You get hosted access to the model for commercial use, with three quality tiers so you can choose the right tradeoff between speed, cost, and output fidelity.

API and Pricing

  • Turbo $0.03 / image
  • Default $0.06 / image
  • Quality $0.10 / image

Per-image pricing, no subscription required. Start with the hosted API and scale up based on the volume your platform needs.