What kind of media can I generate?

Runware supports generation and processing across multiple media types through the Runware API and Playground.

Supported media types

Images

Generate, edit, and process images with capabilities including:

• Text-to-image and image-to-image generation

• Image editing, inpainting, and outpainting

• Upscaling, background removal, and face restoration

• Advanced controls such as LoRAs, ControlNet, and reference images

• Image analysis, captioning, and safety workflows

Video

Generate and transform video using supported models, including:

• Text-to-video

• Image-to-video

• Video-to-video

• Reference-guided and multi-input video generation

• Video editing, continuation, and lip-sync workflows

• Native audio generation on supported models

Audio

Generate and process audio for workflows such as:

• Voice and speech generation

• Music and sound generation

• Audio-driven video and lip sync

• Audio transcription and analysis

Text

Run large language models for text generation, reasoning, structured outputs, and multimodal workflows.

3D

Generate 3D models and assets from text or image inputs using supported 3D models.

Capabilities vary by model, so check the model catalog and individual model documentation to see which inputs, outputs, and features are supported.

For the latest available models and capabilities, see the Runware documentation:
https://runware.ai/docs/models