Renoise AI Models

Every AI video, image and music model inside Renoise — one plan unlocks them all.

ByteDance’s June 2026 preview: native 30-second clips, up to 50 multimodal inputs, stronger control.

Google’s video model with native synced audio — sound and voice generated in the same pass, no post-dubbing. On the Renoise Canvas.

Google's entry-level image model — the lowest-cost image generation on the Renoise Canvas, at 4 credits per image with up to 14 references.

Generate ~30-second instrumental soundtracks with Google’s Lyria — score the AI videos you make on the Renoise Canvas.

ByteDance’s Seedream 5.0 Lite image model — 4K output and up to 14 reference images, on the Renoise Canvas.

xAI’s video model with native audio — sound, dialogue and motion in one pass, on the Renoise Canvas.

Studio-grade images that read perfectly at 4K.

ByteDance’s flagship video model, inside Renoise. Everyone is a director.

ByteDance’s fast, low-cost video tier — for high-volume work, on the Renoise Canvas.

Seedance 2.0 now generates native 4K video in Renoise — every aspect ratio, 4 to 15 seconds, 100 credits per second.

xAI’s Aurora image model — photoreal scenes and sharp text, on the Renoise Canvas.

Kuaishou’s flagship video model — lipsync, multi-shot, one Canvas.

OpenAI’s GPT Image 2, inside Renoise. One prompt, one production-ready image.

Midjourney V7, inside Renoise. The world’s favorite image model, one prompt away.

Google’s Nano Banana 2, inside Renoise — 1K to 4K, native to your Canvas workflow.

By Alibaba ATH, inside Renoise. 15-second multi-shot narratives with native audio, outperforming the field.