Skip to content
Note—001FiledCreators

Pierrick Chevallier: Minimax H3 is honestly ridiculous for motion design when the source image alread

Pierrick Chevallier turned two still K-pop magazine covers into 15 seconds of moving type with MiniMax H3. He has not shared his prompt or said whether the on-beat sound came from the model.

Drafted by The Generated · Filed by The Generated

Pierrick Chevallier's new 15-second piece is a stunning bit of motion design, and it feels like the cover and hero spread of a fashion magazine have been brought to life. Two black-and-white K-pop covers start as still pages, then giant letters sweep across the frame in front of, behind and around the models before every line locks back into the layout.

The movement of the type around the people is pretty much flawless. From the post alone it is hard to tell whether only the text is animated or the models as well; going through the frames, the models move too, with push-ins on each model's face and a silhouette that turns into the final pose.

On-beat sound design lands every hit, so the whole thing could pass for a behind-the-scenes recording straight out of the photo shoot itself. Chevallier (@charaspower), a French VFX artist who credits himself on the second season of House of David, made it with MiniMax H3, the only tool named in his post, and shared the two covers he started from in the replies. It is a beautiful piece of work, and if you have made something like it, tag us so we can take a look.

Every clip is credited to its maker. If one is yours and you want it removed, message us and it comes down.

Source: Pierrick Chevallier (CharaspowerAI) on X, 8 Oct 2026.

Provenance — Pierrick Chevallier (CharaspowerAI) on X, 8 Oct 2026 · Status: verified 9 Oct 2026: maker's own X post re-read via the API
A K-pop magazine cover, brought to life

That’s all of Creators.

10 Oct · 2 notes, filed as the record moved.

Creators & AI Talent — archive

Also filed

Models1 note
OpenAI's 10-minute claim describes Higgsfield's own studio
OpenAI says Higgsfield now makes AI videos over 10 minutes long on GPT-6 Astra, up from about one minute, with voice filmmaking next

OpenAI says Higgsfield users can now make AI videos over 10 minutes long with GPT-6 Astra. Its only example is Higgsfield's in-house tutorial setup, and each scene is still made at up to 30 seconds.

Grimes' team says AI was one tool among 70+ artists
Grimes' 'Accelerando' video used AI 'sparingly', her team says, with 70+ artists on the crew

Grimes' team says AI was a supplementary tool in the Accelerando video, made by more than 70 artists over two to three months. Which shots used AI, and which tools, has not been disclosed.

Disney bids $20M for Character.AI's code, and hires the people who wrote it
Disney bids $20M to be the stalking horse for Character.AI's assets as the chatbot startup files for Chapter 11

Disney bid $20 million to license some of bankrupt Character.AI's code, while most of the startup's staff joined Disney. The app, its users and their chats are not part of the deal, and rival bids can still top it.