Skip to content
Note—003FiledCreators

Rory Flynn: Found footage from Fast & the Furious 🤯

Rory Flynn restages the Charger against Supra showdown as one continuous drone shot, blocked as a Blender previs and generated in Seedance 2.5 per his post. Only the foley feels a little stiff next to the blockbusters.

Drafted by The Generated · Filed by The Generated

American muscle against JDM, the showdown the Fast & Furious franchise made iconic, gets a new scene courtesy of Rory Flynn, and it would feel at home in one of the blockbuster installments. A black Charger and an orange Supra race through an industrial port in one continuous sweeping shot that climbs out to a drone ahead of the cars, takes in a close encounter with a freight train and ends with a sticky meeting with a truck.

It started as a previs, a rough 3D animatic of the shot, out of Blender. Rory used Opus 5.5 and Blender to block the scene in 3D, then generated the finished film in Seedance 2.5, feeding it the previs render alongside car references and location plates. In practice, the previs locks the camera path, the car positions and the crash timing, and the model supplies the look on top of that plan.

Accurate steering, suspension and crash physics, coupled with photorealistic reflections in the paint, add to the realism and believability of the entire short. Only the foley feels a little stiff compared to its blockbuster counterparts. It is a textbook lesson in this workflow, and it is today's Video of the Day on our site.

Rory's references and full prompt are in his thread on X. If you have made something like it, tag us.

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

Source: Rory Flynn (Ror_Fly) on X, 6 Oct 2026.

Provenance — Rory Flynn (Ror_Fly) on X, 6 Oct 2026 · Status: verified 7 Oct 2026: maker's own X post re-read via the API
American muscle against JDM, in one unbroken take
LeadNote—001FiledCreators

Kavan: Chapter Six of Season One of the Magnific Original Series The Chronicles of Bone

Chapter Six of Kavan the Kid's The Chronicles of Bone is haunting, expansive dark fantasy that rivals studio TV. It is a Magnific Original made on a platform that hosts other companies' models, and the models behind this episode are not named.

Drafted by The Generated · Filed by The Generated

Haunting, captivating, deep and expansive, Chapter Six of The Chronicles of Bone builds a world to rival any series or film from a major studio, and you can barely tell it is AI.

The series comes from Kavan the Kid (@kavanthekid), and this chapter was our first encounter with it, though it most certainly won't be our last. Rich, intriguing characters, well-scripted dialogue and blockbuster-quality action carry all 24 minutes, while the mise-en-scène pulls you into the world without the five installments that came before it.

It is genuinely difficult to fault. This is seriously high-quality IP that would stand tall against most of the studio-backed content pumped onto streaming platforms, and the audience is already there: the series' 12 episodes had 40.9 million YouTube views by Wednesday morning, with a new chapter landing roughly once a month.

Production: a Magnific Original from Kavan's studio Phantom X, made on Magnific, a platform that hosts models from other companies. Kavan has named Seedance and Nano Banana for the series, but not the models behind this episode.

Watch the full episode on Kavan's YouTube channel, and if you have made something like it, tag us.

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

Source: Kavan the Kid (Kavanthekid) on X and YouTube, 6 Oct 2026.

Provenance — Kavan the Kid (Kavanthekid) on X and YouTube, 6 Oct 2026 · Status: verified 7 Oct 2026: maker's own X post re-read via the API
A dark fantasy world to rival anything the studios release
Note—002FiledCreators

Calira: Winter luxury, wrapped in white

Calira's 15-second Seedance 2.5 fashion spot sells its slow motion: hair, fur and snow move like real high-frame-rate footage slowed down. The mountains carry no landmark, so it could be anywhere.

Drafted by The Generated · Filed by The Generated

A fur-wrapped woman walks slowly up a mountainside in Calira's new 15-second fashion spot, and the slow motion is what sells it. The frames move the way footage shot at a high frame rate does when you slow it down: her hair bounces and the white fur coat moves exactly as they would in a normal slow-mo shot.

The range behind her has no clear reference point, so it could be the Rockies, the Alps or any other mountains in the world, and it still reads as a real place. A gently rising audio track, the crunch of snow under her boots and a face that holds steady from shot to shot add to the realism. In the final close-up, the light on her cheeks is what you would expect from a sunny day in the mountains. Convincing, simple and somewhat beautiful.

Calira made it with Seedance 2.5 on Flova, as named in the original post, and it is today's Video of the Day on our website. If you have made something like it, tag us.

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

Source: Calira (CaliraVal) on X, 7 Oct 2026.

Provenance — Calira (CaliraVal) on X, 7 Oct 2026 · Status: verified 8 Oct 2026: maker's own X post re-read via the API
Slow motion that moves like the real thing
Creators

Calira's 15-second winter fashion film gets slow motion right

Calira's 15-second winter fashion film, made with Seedance 2.5 on Flova, holds one face across four shots and moves like real high-frame-rate footage slowed down. She published the full prompt, and the post is tagged for Flova's creator partner program; it does not say whether its audio came from the model.

Drafted by The Generated · Filed by The Generated
A woman in a white faux-fur jacket and black trousers walks toward the camera across fresh snow, with sunlit snowy mountain peaks and a dark pine valley behind her

A woman in a white faux-fur jacket walks toward the camera across fresh snow, with a wall of white peaks and a dark pine valley behind her. Her ponytail swings, the fur lifts and settles with each step, and a line of footprints trails back across the snowfield. Fifteen seconds later the camera has pushed in so close that you can see the freckles on her nose and the winter sun catching her cheeks.

The film is "Winter luxury, wrapped in white", posted on X on Wednesday 7 October by Calira (@CaliraVal), an AI content creator who makes photoreal lifestyle and fashion clips. She credits it to Seedance 2.5, ByteDance's video and audio model, used on the Flova platform, and she published the full prompt alongside it. It is our Video of the Day, and it is a convincing, simple and somewhat beautiful piece of work.

Keep reading — 5 min

That’s all of Creators.

8 Oct · 3 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.