The New Black AI
← Journal

The New Black AI now creates fashion videos from text alone

Published 18 September 2026

Image to Video always needed a picture to start from. The New Black AI now creates a fashion video from text alone: write what you want to see, choose the format and the length, describe the sound, and generate. The workflow is now called Create video from text or image, because both still work.

Editorial fashion photograph generated with The New Black AI

What it does

Describe the scene: a model in a red coat crossing a Paris street at night, a close-up of a silk dress moving in the wind: and the clip is generated from the description. Give a start image instead, and the video begins from that frame; add an end image, and the clip travels from one to the other.

Every video workflow in the studio now has an Audio section: describe the voice, the music or the ambience, and the sound is generated with the picture.

How it works

1. Write the scene, or upload a start image and, optionally, an end image. 2. Choose the format and the length. 3. Describe the sound, if you want any. 4. Generate. Standard renders in 720p with generated audio; Pro renders in 1080p.

What it costs

By the second: 2.2 credits per second in Standard, 4.4 in Pro. A 5-second clip is 11 credits in Standard and 22 in Pro.

Why it matters for a brand

A moodboard sentence becomes a moving reference before a single sample exists. A product that is still a sketch can be shown in motion to a buyer, and a campaign idea can be tested as a clip before the shoot is booked.

For a clip built around a real product, the dedicated workflows are more precise: Model Walk, Product 360, UGC Video. Resolution and audio options across all video workflows are described in 720p, 1080p and audio. Details on the feature page.

Frequently asked questions

Do I still need an image?+

No. Text alone is enough; a start image and an end image are optional.

What resolution do I get?+

720p in Standard, 1080p in Pro.

Is the sound generated too?+

Yes, from the description you write in the Audio section.