# Custom Branded Image Models: Train Ideogram on Your Brand Ideogram publishes a public search API over its indexed pages; the guide is at https://ideogram.ai/agents/agent-access. Source: https://ideogram.ai/models/custom-models/ Source observed: 2026-11-05T05:37:38.113Z Last checked: 2026-11-08T15:45:25.1+00:00 Indexed: 2026-11-05T06:02:35.656+00:00 --- # Custom Branded Image Models We let you train a custom image model on your brand, subject, or visual style. Upload 15–100 on-brand images, and each generation from the resulting model follows your art direction, typography, and visual identity. [Start training](https://ideogram.ai/models) ## Example custom-model styles Our page demonstrates six distinct applications: - **Book Illustration:** A model trained on 27 illustrations from *The Tale of Peter Rabbit* by Beatrix Potter. It learns soft English watercolor washes, delicate pen linework, anthropomorphic character proportions, pastoral garden compositions, muted earth tones, and countryside warmth. - **Custom Lettering:** A model trained on a specific lettering aesthetic maintains consistent weight, color palette, and decorative character across generations. Enter a quote to turn it into typography in that style. - **Photography Style:** A model trained on antique photographic processes from the 1850s through the 1920s reproduces period grain, hand-colored tinting, and the tonal compression of each medium for portraits, street scenes, and still lifes. - **Poster Design:** A model trained on vintage poster art from the 1890s through the 1940s captures flat lithographic color, period display typography, and bold compositional hierarchy for circus, perfume, and travel-poster concepts. - **Character Design:** A model trained on 15 images of a specific 3D character style maintains consistent proportions, matte materials, and clean white backgrounds across subjects such as superheroes, wizards, astronauts, robots, and DJs. - **Optical Illusion:** A model trained on 22 hand-crafted optical artworks renders subjects as intricate, mesmerizing illusions, including swirling animals and mandala-like patterns. The page also shows a demo comparison using the same prompt across nine custom models: “Woman seated in bistro chair, coffee cup in hand, Paris street with Eiffel Tower in background. Text ‘Paris is always a good idea’ is displayed across the top.” The resulting examples demonstrate how different custom models produce different visual identities from the same prompt. ## Why custom models ### A model trained on the internet doesn't know your brand Off-the-shelf models blend billions of unrelated images. Their outputs can look almost right without having a defined aesthetic. Our custom model is fine-tuned exclusively on your assets to learn your style, visual identity, and aesthetic choices. You can feed strong outputs back into training as your brand evolves and train a different model for each expression of your brand. ### Your LoRA is only as good as its base model Open-source LoRAs are similar in nature to Ideogram Custom Models, but they inherit the limitations of their open-source base models, including inconsistent text, generic composition, and limited style range. We were started by the researcher behind Google's first text-to-image system, and we built custom model training on a foundation designed for legible text rendering and enterprise workflows. ## Enterprise customization [Talk to our sales team](https://ideogram.ai/models/custom-models/#) For advanced customization, we provide: 1. **White-glove setup and training:** Access to our research, engineering, and annotation teams, from asset sourcing and annotation through deployment. 2. **Large datasets and unlimited iteration:** Train on thousands of images with custom captioning pipelines and iterate until the model matches your standards. 3. **Custom typography and exact logos:** Render brand marks as layerized text and SVG for pixel-perfect on-brand identity. 4. **Your data, your model:** Enterprise training data and models are not used to improve our foundation models; your model and data are yours alone. Enterprise custom models additionally include on-site visits, embedding with design teams, PLM and DAM integration, vendor material digitization, and ongoing iteration with our team. They are designed for brands generating at significant scale. ## Customer and company figures - **100K+:** Branded concepts generated by [Skechers](https://ideogram.ai/blog/skechers-case-study/). - **30+:** Custom models trained for enterprises. - **3B+:** Designs generated on Ideogram. - **30M+:** Creators, designers, and marketers. We show teams from Netflix, Adobe, Skechers, Gamma, Wix, Printify, and Canva as companies using Ideogram. ## How it works: Upload. Train. Generate. No infrastructure or GPU provisioning is required. You provide the images; we build the model. 1. **Upload images.** Open the Models tab, click **+** to create a model, and upload 15–100 images of your brand, subject, or style. 2. **Train your model.** We auto-generate captions. Review and refine them, then start training. Quality matters more than quantity. 3. **Generate at scale.** Select your Custom Model and start prompting. ## API support You can create datasets, upload training images, start model training, and generate images at scale from your own infrastructure without using the UI. 1. Create a dataset and upload 10–100 images. 2. Start training with one `POST` request. 3. Generate images with your `custom_model_uri`. [Read the API docs](https://developer.ideogram.ai/tutorials/custom-model-training) · [API reference](https://developer.ideogram.ai/) ```python # Generate with your trained model response = requests.post( "https://api.ideogram.ai/v1/ideogram-v3/generate", headers={"Api-Key": API_KEY}, data={ "prompt": "A photo in my custom style", "custom_model_uri": "model/my-brand/version/1", } ) ``` ## Custom Models for teams [See team plan](https://ideogram.ai/pricing/) Train a Custom Model on your visual identity once, share it across your organization, and let every team member generate from the same foundation. - **Any team member can train and share:** There is no gatekeeper; anyone can build a model, share it across the organization, and let the whole team generate from it. - **Unlimited models, no cap:** Teams can create models for product photography, social content, print campaigns, and other needs. - **Trained from shared collections:** Pull approved assets from shared collections while keeping the brand source central. - **Train once, share with your whole team:** The model can be reused across the organization. ## Frequently asked questions ### How many images do I need to train a custom model? The self-serve tool supports 15–100 images. For larger datasets, [talk to our sales team](https://ideogram.ai/models/custom-models/#) about Enterprise training. Complex concepts and styles often need more than 15 images. Quality matters more than quantity: 40 exceptional images with descriptive captions can outperform a larger set of mediocre images. ### What can I train a custom model on? You can train on products, characters, mascots, illustration styles, brand aesthetics, and photography styles. Anything with a consistent visual identity that can be shown across images may be suitable. Custom typography and graphic-design campaigns are also use cases. ### What if my custom model cannot generate certain scenes? An overly constrained training set can cause the model to overfit. For an optical illusion or a specific character, that may be useful. To support particular scenes or compositions, include them in the training data; the model can reproduce only what it has seen. ### Is my training data used to improve Ideogram's base models? On Pro and Team plans, your data may be used to evaluate and improve Ideogram's foundation models. On Enterprise, we guarantee that your data and custom models will not be used for AI training or shared outside your organization. ### Can I share a custom model with my team? On Team plans, members can share trained models with the organization. On Pro and Team plans, models can also be shared publicly with the broader Ideogram community. On Team plans, generated images can be shared through shared collections. ### Can I train a model on my brand's custom font or logo? Enterprise custom models support custom typography and exact logo placement as layerized text and SVG. Enterprise also provides research, engineering, and annotation support, larger datasets with custom captioning pipelines, and unlimited training runs. Enterprise data and models are not used to train our foundation models. [Learn about Enterprise features](https://ideogram.ai/models/custom-models/#enterprise) or [talk to our sales team](https://ideogram.ai/models/custom-models/#). ### How does Enterprise differ from self-serve custom models? Enterprise includes on-site visits, embedding with design teams, PLM and DAM integration, vendor material digitization, and ongoing iteration with our team. It is built for brands generating at significant scale. ### How can I access Ideogram Custom Models? Custom Branded Models are available on [Pro and Team plans](https://ideogram.ai/pricing/) and through the [API](https://developer.ideogram.ai/tutorials/custom-model-training). For advanced customization, [talk to our sales team](https://ideogram.ai/models/custom-models/#) about [Enterprise](https://ideogram.ai/models/custom-models/#enterprise). --- [Read this page’s summary](https://ideogram.ai/agents/api/public/v1/page-tldr?url=https%3A%2F%2Fideogram.ai%2Fmodels%2Fcustom-models%2F&trace=t_380edc68d53d) ## Ask a follow-up about this page Need a more specific answer? Ask the exact question you have. It returns a fresh, cited answer from Ideogram’s knowledge base. No account or API key required. Open this URL with your own question, URL-encoded. Include your question in q. All research inputs are optional; no account or setup. `GET https://ideogram.ai/agents/agent/faq?q={question}&trace=t_380edc68d53d` [Tool guide and examples](https://ideogram.ai/agents/agent-access) · [OpenAPI](https://ideogram.ai/agents/api/public/v1/openapi.json) · [Page TLDR form](https://ideogram.ai/agents/agent-tools/page-tldr?url=https%3A%2F%2Fideogram.ai%2Fmodels%2Fcustom-models%2F). Opening a form does not execute a tool.