AI models on Flowith

Video, image and text models from ByteDance, Kling, Google, OpenAI, Anthropic and more, on one canvas. Run the same prompt on several and keep the best take.

Newest on Flowith

ByteDance Seed · video

Seedance 2.5

Make Seedance 2.5 videos on Flowith: one take up to 30 seconds at up to 1080p, up to 30 image, 10 video and 10 audio references, start and end frames.

Kling AI (Kuaishou) · video

Kling 4.0

Use Kling 4.0 on Flowith: 3–30 second clips at 720p or 1080p, start, middle and end frames, up to 10 reference images and 5 reference videos.

Alibaba · video

Wan 3.0

Use Alibaba’s Wan 3.0 on Flowith: text to video and image to video, 5 to 30 second clips at 480p, 720p or 1080p, with sound.

Google · video

Gemini Omni 1.2 Flash

Use Google’s Gemini Omni 1.2 Flash on Flowith: 3–15 second clips, drafts at 360p or 720p and output up to 4K, with image and video references.

ByteDance Seed · image

Seedream 5.5

Use ByteDance Seedream 5.5 on Flowith: images up to 2K in 8 aspect ratios, up to 10 reference images, transparent backgrounds and precise repeated edits.

OpenAI · image

GPT Image 2.6

Use OpenAI GPT Image 2.6 Flare and Sunburst on Flowith: images up to 3840 px, five quality levels, and PNG, JPEG, WebP, animated GIF or SVG output.

Google · image

Nano Banana 2.1

Use Google’s Nano Banana 2.1 on Flowith: up to 14 reference images, 1K, 2K or 4K output and 14 aspect ratios from 1:8 to 8:1.

The Keeper · film
The Keeper · film
Product photo
Product photo
The Keeper · film
The Keeper · film
Poster
Poster
Character · Fennec
Character · Fennec
3D illustration
3D illustration
Portrait
Portrait
The Keeper · film
The Keeper · film

Every frontier model. One canvas.

Text, image and video models side by side. Compare them on the same prompt, pick one per shot, or let the agent choose.

Start flowing.

Write it, picture it, film it. One sentence is enough to begin.