
IMAGE
Make or edit a visual
Describe what to create, or use a supported image as a reference. Check the chosen model’s input limits before uploading.
AVAILABLE MODES & WORKFLOWS
HOW CHAT FITS YOUR WORKFLOW
Use the conversation to organize subject, setting, and intended output. Choose an image, video, or audio workflow; supported inputs and controls depend on the selected model.

IMAGE
Describe what to create, or use a supported image as a reference. Check the chosen model’s input limits before uploading.

VIDEO
Start from text or a supported reference image. Duration, aspect ratio, and output settings vary by model.

AUDIO
Describe genre, mood, tempo, or speech guidance when supported. Available outputs and controls depend on the selected audio model.
Tell the Agent the audience, subject, action, format, and constraints. Confirm the active mode and model controls before submitting a generation.
Use the conversation and workspace to review generations. A different prompt or model setting can change details, so inspect each result before continuing.
A PRACTICAL WORKFLOW
You choose the mode and review the available controls. Model support, settings, and credit use can differ from one task to the next.
Select image, video, or audio. Write the subject and intended result; attach a reference only when the selected workflow accepts it.
Review the model and generation controls shown for the selected task. Credit cost depends on the model and settings.
Inspect the result for unwanted details. Adjust the prompt or settings and run another generation when needed.
AGENT WORKFLOW NOTES
The Agent interface supports image, video, and audio workflows. Available actions depend on the active mode and configured models; use the corresponding studio controls to see current options.
Automatic mode can route eligible requests to supported generation tools. Model inputs and settings still vary by workflow, so review the active mode and controls before submitting.
Yes, when the selected workflow and model accept image references. The upload control shows supported formats and limits; only upload images you have permission to use.
Use the model selector in the active mode for the current list. Availability, input support, and controls can change, so the selector is more reliable than a fixed model list.
There is no single duration for every video model. Check the duration and aspect-ratio controls shown for the model you selected before generating.
The audio catalog can include speech and music models. Voice, language, lyrics, and output controls depend on the selected model and are shown in the audio workflow.
Image, video, and audio tasks use the shared credit balance. The displayed cost depends on the model and settings; review it in the composer or studio before submitting.
See the Privacy Policy for details on account data, uploads, generated media, and service providers. Only upload material you have the right to use.
Sign in or create a Snapgen AI account to use the Agent and manage your conversations, generations, and credit balance.
Use the support link in the site footer and include the relevant page or task ID. Do not send passwords or API credentials.

Use Snapgen AI Agent to organize an idea, then review the active mode, model settings, and credit cost before generating.