Ideogram 4.0
Ideogram 4.0 is an open image model at the forefront of design, built for open weights, multilingual text, precise layout control, editable elements, and realistic 2K images. It is a state-of-the-art open-weight image model for developers and enterprises that want to build, fine-tune, and run visual intelligence on their own hardware. 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. This approach is designed to help the model understand composition before recreating it, giving teams more control over layout, objects, typography, and visual structure. It is built for real design work, especially brand, advertising, fashion, marketing, food, apparel, social, photography, and illustration use cases. Ideogram has led on text rendering since launch, and 4.0 adds bounding-box layout control so headlines stay readable.
Learn more
P-Image-Ideogram
P-Image-Ideogram is a family of Pareto-optimal text-to-image models built by Ideogram with Pruna AI to deliver a strong balance of image quality, generation speed, and efficiency. Designed for high-volume production and rapid iteration, it produces 1K images in seconds while maintaining quality near leading image models. Four Quality levels let users match compute to the brief rather than follow a simple worse-to-better ladder. Medium serves as the everyday default, High is suited to dense typography, complex prompts, and fine details, and Very Low or Low support drafts, testing, and broad A/B exploration. Developers can access the model through a synchronous API endpoint and submit either a natural-language prompt or a structured Ideogram 4.0 JSON prompt, which the server detects automatically. Optional prompt upsampling can expand instructions through Magic Prompt, while a fixed seed supports reproducible results.
Learn more
FLUX 3 Image
FLUX 3 Image is an AI image generation and editing model from Black Forest Labs designed to provide precise control over image composition and individual visual elements. It supports text-to-image generation with prompt following and lets users position elements using bounding boxes on a coordinate-based canvas. Users can perform multiple targeted edits while keeping specified parts of the original image unchanged. The model can also combine as many as 10 reference images into a single composed image, allowing specific objects, clothing, styles, and other visual references to be incorporated into a new result. FLUX 3 Image supports native 2K and 4K rendering to preserve details such as textures, faces, and colors, along with pixel-level editing of selected image regions. The model is also designed for use by AI agents and is available under a commercial weights license for organizations that want to fine-tune and deploy image generation on their own infrastructure.
Learn more
Hy Image 3.5
Hy Image 3.5 is Tencent Hunyuan’s next-generation image generation model, designed to improve the full path from intent understanding to visual expression. It supports text-to-image, image-to-image, reference-based generation, and multi-round conversational editing in a unified workflow. Users can provide text together with reference images, preserve previous context across turns, and continue refining or modifying an image without restarting the creative process. The model can work with multiple reference images in a single request, making it suitable for subject consistency, composition control, product visuals, character creation, advertising materials, and iterative design. It supports a wide range of aspect ratios and output sizes, with custom dimensions and high-resolution generation available through the API. Hy Image 3.5 Preview uses a chat-style messages protocol, allowing image creation and editing instructions to be expressed naturally.
Learn more
