Create media with 400+ models
Generate images, videos, audio, 3D assets, and text with a live catalog of 400+ AI models. Choose video models such as Seedance, Veo, Kling, MiniMax, and Wan; image models such as GPT Image, Nano Banana, Seedream, FLUX, and Qwen; 3D models from Hunyuan and Tripo; plus audio models from Suno, ElevenLabs, MiniMax, and Seed Audio.
With this plugin, you can:
• Generate and edit images from text, images, or supported references.
• Create text-to-video, image-to-video, and reference-to-video clips; use supported video editing, avatar, and motion-control workflows.
• Turn text or images into 3D assets; create speech and music; transcribe audio; and run supported LLMs.
• Search the live model catalog, inspect each model’s inputs, output type, and pricing, upload source media for a generation task, and track asynchronous jobs to completion.
Connect your Atlas Cloud account in the browser—no API key is required. Billable jobs charge your Atlas balance and may require confirmation before submission. Availability, inputs, output formats, processing time, and cost vary by selected model. Uploads are temporary generation inputs, not permanent file storage.
When connected to Atlas Cloud, ChatGPT may share relevant chats and memories with this app to help provide context for your requests. Atlas Cloud’s use of this data is subject to their terms and privacy policy. If you have Memory enabled, data from the app may be used to proactively provide helpful information or suggestions. ChatGPT always respects your training data preferences, including for data from connected apps. Use of apps may come with elevated risk. You can manage your preferences or disconnect from apps anytime in your settings. Learn more