GPT Image 2.6 Now live in Flare and Sunburst. Make pictures from text or edit your photos, up to 4K.
Try itSeeDream V4 is part of the Seedream 4.5 family.
See Seedream 4.5SeeDream V4 AI image generator
ByteDance advanced model for creative image generation
From 9 tokens an image. Free tokens on signup, no card required. Plans from $19 one time.

Key features
SeeDream V4 turns a written prompt into images inside Enhance AI.
Input modes
SeeDream V4 works from a written prompt. Describe the subject, the setting, the light and the style in plain words and pick a size before you generate. Short, concrete prompts tend to render more reliably than long lists of adjectives, so say less and say it clearly.
Specifications
- Price
- From 9 tokens an image
- Type
- Image
- Modes
- Text to image
How to use SeeDream V4 on Enhance AI
- 1
Sign in and pick SeeDream V4
Press Try on this page to open the Playground with SeeDream V4 selected. A new account starts with free tokens, no card needed.
- 2
Describe the image
Write what you want to see: the subject, the setting, the light and the style. Pick a size and how many variations you want, and keep the prompt to one idea per image.
- 3
Generate, then download
Press Generate. You see the cost before you confirm, and the images land in your history, ready to download or edit.
Common questions
- What is SeeDream V4?
- SeeDream V4 is an image generation model. It turns a written prompt into images.
- Is SeeDream V4 free to try?
- Yes. Every new account gets free tokens on signup, no card required, so you can run SeeDream V4 before paying anything. Plans from $19 one time add more tokens when you need them, and one account covers SeeDream V4 and all the other top models.
- What does it cost to run SeeDream V4?
- One SeeDream V4 image costs from 9 tokens. Image generations are billed in tokens, and every new account starts with free tokens. You see the cost before you generate.
Related models
- GPT image 2.5 SunburstGPT Image 2.5 Sunburst is OpenAI’s high-precision model for complex image generation and targeted editing. Accepting text and reference images, it maintains exact subject consistency and texture quality across revisions. It is available via the Images and Responses APIs with six adjustable quality settings.View
- GPT Image 2OpenAI GPT Image 2 — high-quality image generation and editingView
- Flux 2 TurboUltra-fast Flux 2 Turbo model for rapid high-quality image generationView
- Qwen Image 2 ProQwen Image 2.0 Pro — advanced image generation with Chinese & English supportView
- Qwen ImagePowerful image foundation model with complex text renderingView
- Nano Banana 2Google Nano Banana 2 model for high-quality image generationView
More from Enhance AI