Skip to main content

​
Images, sprites, and video through one API

Generate and edit images, remove backgrounds, upscale, and create reference-based sprite animations through the DreamLayer Agent API, CLI or MCP server. Create logo concepts, product imagery, marketing visuals, print artwork and game assets, then save the results into your project. Ordinary image operations cost one credit each; sprite bundles use frame-count pricing. Create videos from text or one reference image through the REST API, with sound on by default. Review and accept a credit quote before generation. Video uses your API key and API credit balance, with its own documented settings and recovery flow.

Use the Agent API

One key, one endpoint. Streamed progress, resumable events, and durable jobs.

Work from the command line

Generate and edit images over local files without leaving your shell.

Give an AI agent image tools

One line in an MCP client config. No clone, no local install.

Read the endpoint reference

Conversations, executions, events, assets, idempotency, and errors.

Create a video

Text or image to MP4, sound, quotes, progress, and downloads.

Create a sprite sheet

Reference-based animations and custom instructions up to 4,000 characters.

​
Build around the public contract

Use documented request fields, execution states, approved credit amounts, and owned download URLs. The guides focus on those integration fields, not internal processing details. Keep raw responses and request content out of public logs.

​
V1 scope

Image operations support text-to-image, one-reference-image image-to-image, background removal, and upscale, plus persistent conversations, multiple turns, and durable jobs. Sprite sheets add reference-based animation bundles. Video supports text-to-video and one-reference-image image-to-video through a separate quote-first workflow; it does not inherit image conversation state.

​
Build a reliable integration

Start with the API overview, then use runnable examples, request limits, and safe retries. Connect an AI client using the MCP setup guide, or install the CLI using the command-line guide.

​
What you can build

Install the agent workflows for task instructions, credit checks, recoverable jobs and local Godot/Unity import examples.
  • Product image workflows: edit a reference, remove backgrounds, or upscale images while preserving a separate execution for each asset.
  • Game asset tools: turn a reference into a sprite-sheet animation with exported frames and playback metadata.
  • Video clips: describe a scene or animate a reference, choose sound or silence, and download the MP4.
  • Agent workflows: connect MCP tools so an assistant can inspect capabilities, check credits, and return a finished asset.
  • Scheduled media jobs: use CLI automation or a bounded API queue with saved request identity and recoverable outputs.