wan-2-2/text-to-image
Generate high quality images from text prompts with Wan 2.2 Plus.
OpenAI's GPT Image 2.6 Sunburst Text To Image spends extra time on each render to deliver fine detail, steady textures, and exact lettering at up to 4K, with GIF and SVG options.
Trading retouching passes for first-try polish, GPT Image 2.6 Sunburst suits brand designers, agencies, and product teams shipping final artwork.
For developers, GPT Image 2.6 Sunburst on RunComfy can be used both in the browser and via an HTTP API, so you don't need to host or scale the model yourself.
Ideal for: Brand Campaign Artwork | Premium Product Imagery | Editorial Posters
GPT Image 2.6 Sunburst is the precision tier of the GPT Image 2.6 family. Each image takes longer than on Flare, and that time goes into crisper materials, cleaner edges, and more consistent small details.
GPT Image 2.6 Sunburst shares the same controls as Flare, including looping GIF and vector SVG output, so you can move a prompt between the two tiers without rewriting it.
| Parameter | Required | Type | Default | Range / Options | Description |
|---|---|---|---|---|---|
| prompt* | Yes (*) | String | — | — | Plain-language description of the image, including any text it should show. |
| aspect_ratio | No | String | 1:1 | 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 2:1, 1:2, 3:1, 1:3, 9:21 | Frame shape, from square to 3:1 panoramas. |
| resolution | No | String | 1k | 1k, 2k, 4k | Output size tier. |
| quality | No | String | medium | low, medium, high, xhigh, max | Rendering effort; higher tiers cost more. |
| complexity | No | String | high | low, medium, high | Layout planning before drawing; same price at every level. |
| output_format | No | String | png | png, jpeg, webp, gif, svg | Still image, looping GIF, or vector SVG. |
| frame_count | No | Integer | 9 | 2 – 16 | GIF only: number of frames. |
| frame_duration_ms | No | Integer | 200 | 20 – 2000 | GIF only: display time per frame in milliseconds. |
| Quality | 1K | 2K | 4K |
|---|---|---|---|
| low | $0.048 | $0.080 | $0.143 |
| medium | $0.080 | $0.138 | $0.238 |
| high | $0.095 | $0.159 | $0.285 |
| xhigh | $0.169 | $0.285 | $0.507 |
| max | $0.380 | $0.634 | $1.056 |
Prices are per output image.
Generate high quality images from text prompts with Wan 2.2 Plus.
Generate images from text prompts with Wan 2.5 Preview.
Edit images precisely and fast with FLUX Kontext Pro.
Edit and fuse images into high quality results with Seedream 4.0.
Prompt-to-visual engine with precise layout and typography control
Turn sketches into precise 2K-4K visuals with smart correction and seamless creative control.
GPT Image 2.6 Sunburst is OpenAI's precision tier of the GPT Image 2.6 family, built for polished images with fine, consistent detail. Designers and brand teams use GPT Image 2.6 Sunburst for campaign artwork, premium product imagery, and editorial posters that need little retouching.
Both accept the same parameters, but GPT Image 2.6 Sunburst takes longer per image and uses that time for crisper materials and steadier small details. Flare is the better pick for fast exploration, while GPT Image 2.6 Sunburst suits final, delivery-grade renders.
GPT Image 2.6 Sunburst is designed to produce clean, readable lettering for headlines, labels, and small print on posters, packaging, and ads. Quote the exact words in your prompt and describe font style and placement to get the most reliable typography from GPT Image 2.6 Sunburst.
Yes. With output_format set to gif, GPT Image 2.6 Sunburst returns a looping animation of 2 to 16 frames, and frame_duration_ms sets each frame's display time from 20 to 2000 ms. With svg, GPT Image 2.6 Sunburst returns a scalable vector, best suited to flat icons, logos, and illustrations.
Quality in GPT Image 2.6 Sunburst ranges from low to max and controls rendering detail and price. Complexity (low, medium, high) sets how much GPT Image 2.6 Sunburst plans the layout before drawing; high helps busy, multi-subject scenes and does not change the cost.
GPT Image 2.6 Sunburst renders at 1k, 2k, or 4k across fifteen aspect ratios, from 1:1 squares to 9:16 stories and 3:1 panoramas. For exact pixel sizes, check the current RunComfy parameter panel for GPT Image 2.6 Sunburst.
Yes. Refine prompts for GPT Image 2.6 Sunburst in the RunComfy model UI, then call the same model via the RunComfy API with identical parameters. This makes GPT Image 2.6 Sunburst easy to add to design tools and content pipelines without hosting it yourself.
GPT Image 2.6 Sunburst is billed per output image by quality and resolution, from $0.048 for low quality at 1K and $0.080 for medium at 1K up to $1.056 for max quality at 4K. GIF output on GPT Image 2.6 Sunburst costs about the image price × (1 + frame_count / 16), SVG adds $0.015 to $0.016, and new users typically get free trial credits.
RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
