Choose the image model
Select the model whose text, product, character or style strengths fit the job.
ACTIVE · VERIFIED AGAINST THE PRODUCT
AI Image Generation
Create and edit AI images with 20 active models from OpenAI, Google, ByteDance, Krea, Recraft, Kling, Black Forest Labs, Runway and Wan. Use up to 14 reference images and output up to 4K on supported models.
Focused AI image guides
Choose a guide for models, cost or comparison
Dedicated pages explain the multi-model workspace, credit controls and how to choose a model for each image job.
Verified operating specifications
Real inputs, limits and controls
- Model catalog
- 20 active models across nine provider families
- Outputs
- Up to four images per task and up to 4K where supported
- References
- Up to 14 images, 5 MB each, addressed with @img tags
- Prompt and cost
- Model-dependent prompts up to 10,000 characters; live credit quote
Core capabilities
What this tool does
20 active models across nine families
Text-to-image and reference editing
Up to four images per task
Up to 4K on supported models
Connected services
Related voice sources, services or models
OpenAIImage model provider
GoogleImage model provider
ByteDanceImage model provider
KreaImage model provider
RecraftImage model provider
KlingImage model provider
Black Forest LabsImage model provider
RunwayImage model provider
WanImage model provider
20 active models
Current image model inventory
ByteDance
04Seedream 5 Pro · Seedream 5 Lite · Seedream 4.5 · Seedream 4
Recraft
01Recraft 4.1
OpenAI
03GPT Image 2 · GPT Image 1.5 · GPT Image 1
Google
04Nano Banana 2 Lite · Nano Banana Pro · Nano Banana 2 · Nano Banana
Krea
02Krea 2 Medium · Krea 2 Large
Kling
01Kling O1 Image
Black Forest Labs
02FLUX.2 Pro · FLUX.1 Kontext Pro
Runway
02Gen-4 Image · Gen-4 Image Turbo
Wan
01Wan 2.5 Image
Product workflow
From input to finished output in three steps
Prompt and reference
Describe the result, add up to 14 assets and address them with @img1, @img2 and so on.
Quote, generate and reuse
Review the live credit estimate, create up to four images and drag a result back in as a reference.
Use cases
Good fits
- Product visuals and ads
- Infographics with text
- Character-consistent scenes
- Reference-based editing
Developer API
Integrate this workflow
Generation tasks are asynchronous: receive a task_id, then poll or use a webhook.
GET/v1i/modelsPOST/v1i/task/pricePOST/v1i/task/generate-imageProduct-verified information
This page only describes capabilities visible in the current application with a corresponding processing path at the latest verification.