
Create images from a brief
Describe a product shot, illustration, or campaign concept and ask your assistant to generate it with an available image model.

Connect Whisk AI to ChatGPT and Claude. Generate images and videos with multiple image and video models using your existing credits.
After copying, paste the URL, add the connection, and authorize Whisk AI.
Use your Whisk AI account. No API key needed. Organization accounts may require an administrator to enable custom connectors.
After connecting and enabling Whisk AI, try creating a polished product showcase with GPT Image 2.5.
@Whisk AI Before generating, check whether Whisk AI is connected and available. If it is not, ask me to connect it first. Then use the Whisk AI MCP with GPT Image 2.5 to create a product showcase with soft studio lighting, a clean composition, and a premium commercial aesthetic.
The link pre-fills an example prompt. Select your connected Whisk AI app in chat if needed.
Start creatingWhisk AI MCP / 01
Bring your ideas, references, and creative direction into the conversation.

Describe a product shot, illustration, or campaign concept and ask your assistant to generate it with an available image model.

Choose a supported model and use a reference image to explore motion, scenes, and short video concepts.

Choose an image from your Whisk AI library or upload a reference on the website to guide your next creation.

Ask your assistant to check model settings, your credit balance, and an estimated cost before submitting a task.
Whisk AI MCP / 02
Explore the models available through Whisk AI MCP. Options and reference limits depend on the model you choose.
Duration, resolution and reference modes vary by model
Resolution and reference limits vary by model
Whisk AI MCP / 03
Explore the models available through Whisk AI MCP. Options and reference limits depend on the model you choose.
No API key · Existing credits · Your Whisk AI library
Ask your assistant to check model settings, your credit balance, and an estimated cost before submitting a task.
No API key · Existing credits · Your Whisk AI library
Whisk AI / 04
Open these website tools to refine your images after creating.
MCP uses your existing Whisk AI credits. Cost depends on the selected model and settings; your agent can check an estimate before submitting.
Image generation and editing: Nano Banana 2, Nano Banana Pro, Nano Banana 2.1, Nano Banana Lite, GPT Image 2.5, and Seedream 4.5. Video: Kling 3.0, Grok Video, Grok Video 1.5, Kling 4.0, Seedance 2.0, Seedance 2.0 Mini, Seedance 2.5, Sora 2, and Sora 2 Pro. Read each model’s parameters before generating.
Chat image import is being tested with ChatGPT: attach a JPEG, PNG or WebP (up to 8 MB) and ask your agent to save it as a reference, without copying an asset ID. Claude attachment transfer is still unverified; use the website upload or select a library image for now. Video reference files are not supported yet.
Generations run as background tasks. Your agent can check progress or share a link to your workspace. A status timeout does not mean generation failed; avoid submitting the same task again.
Open Connected apps while signed in and revoke the connection. This stops future access; generations you already submitted can still finish.
Connect Whisk AI to your assistant and create with your existing credits.
Connect your AI