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.
How to use
- 1Add it in ChatGPT
Open Atlas Cloud in ChatGPT's Plugin directory (button above), select + to add it and sign in if asked.
- 2Use it in a chat
Type @ in the composer and pick Atlas Cloud, or start your message with its name. ChatGPT may also suggest it when it fits what you ask.
Skills 3
- media-generation
Quickly call 300+ AI image generation, video generation, audio (TTS, music, speech-to-text), 3D generation, and LLM models through a unified API. Use this skill when the user needs to integrate AI image generation (e.g., Flux, Seedream, DALL-E), AI video generation (e.g., Kling, Sora, Seedance), call LLM APIs (OpenAI-compatible format), generate speech/TTS or music (e.g., Seed Audio, Suno), transcribe audio to text (ASR), or turn images/text into 3D assets into their project. Also covers model discovery and keyword search, uploading local images/media files, one-step quick generation, and configuring ATLASCLOUD_API_KEY. Even if the user doesn't explicitly mention Atlas Cloud, this skill should be considered whenever AI media generation API integration development is involved.
- seedance-skill
Plan and generate controllable Seedance video using Seedream 5.0 Pro storyboards and Seedance 2.0 today, with a Seedance 2.5 route when available. Use for consistent people, products, objects, food, or scenes; storyboard-to- video; reference-to-video; first-and-last-frame image-to-video; extensions; and Atlas Cloud media generation.
- universal-video-prompt-skill
Write one model-agnostic video prompt spec, then compile it to whichever video model you can actually call. Use for cross-model prompt work, model comparison matrices, reusing one brief across providers, or when the target model is not yet available and the work must proceed on another one.
Things to ask
- “Use Seedance 2.5 to create a 30-second video of a dog running on a beach”
- “Generate a studio image of a purple wireless speaker with GPT image 2.5, 16:9”
- “Create a textured 3D model of a small orange robot toy”