GPT Image 2.5 Sunburst

GPT Image 2.5 Sunburst is OpenAI’s most capable image model. Generate images from text or edit existing images with precise, instruction-following control. Sunburst is tuned for workflows where editing precision matters most.

What it does

Sunburst handles two workflows: generating images from text descriptions, and editing existing images with specific instructions. It follows your directions closely while keeping the parts you want unchanged.

When you pass reference images, Sunburst processes them at high fidelity automatically. Pass one image to edit it, or pass multiple images to combine styles, subjects, or references into a single output.

Quality settings

Sunburst supports six quality settings: low, medium, high, xhigh, max, and auto (the default). Lower quality is faster and cheaper; xhigh and max push detail and fidelity further for final assets. Start with low for drafts and step up when the image needs it.

Key capabilities

Photorealism and detail: Natural-looking images with accurate lighting, believable materials, and rich textures.

Text rendering: Dense text, small lettering, and complex layouts like infographics, UI mockups, and marketing materials.

Precise editing: Targeted changes without reinterpreting the entire image. The model preserves identity, composition, and lighting while you adjust specific elements.

Style control: Apply consistent visual styles across different subjects, or transfer the look of one image to another with minimal prompting.

Use cases

Image generation: Infographics, logos, UI mockups, photorealistic scenes, comic strips, marketing visuals.

Image editing: Style transfer, virtual clothing try-ons, product mockups, text translation in images, lighting adjustments, object removal, scene compositing. Insert people into new scenes while preserving their likeness, or swap furniture in room photos without changing the camera angle.

Character consistency: Build multi-page illustrations where characters look the same across different scenes.

How to get good results

Be specific: Instead of “make it better,” say “add soft coastal daylight” or “change the red hat to light blue velvet.”

Use photo language for realism: Mention lens type, lighting quality, and framing. “Shot with a 50mm lens, soft daylight, shallow depth of field” gets you closer to real photography.

Lock what shouldn’t change: When editing, state what must stay the same. “Change only the lighting, preserve the subject’s face, pose, and clothing.”

Put text in quotes: For readable text, put the exact copy in “quotes” and describe the typography.

Inputs

• prompt: What you want to generate or how to edit the input
• input_images: One or more reference images (for editing or composing)
• aspect_ratio: Named ratios (1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16), auto, or explicit sizes like 1024x1024
• quality: low, medium, high, xhigh, max, or auto
• number_of_images: Generate up to 10 images in a single call
• output_format: webp (default), png, or jpeg
• background: auto, transparent, or opaque
• moderation: auto (default) or low for less strict content filtering
• openai_api_key: Optional — bring your own OpenAI API key to pay OpenAI directly

You can try this model on the Replicate Playground at replicate.com/playground.