Higgsfield animation team shares full AI pipeline: 18 shots of a car chase in 3 days
xiaohu · x · 2026-09-28
Higgsfield's traditionally-trained animation team released a 28-minute breakdown of how they completed an 18-shot car chase for their short film Passport Rush in 3 days, despite having never used AI before.
Key practices:
- Route shots at storyboard stage: complex action/camera work goes through Blender previs; simple shots go straight to text-to-video. Storyboards only lock story beats, leaving room for generation unpredictability
- Asset-first approach: the quality of character/prop/background reference images determines final quality, with a dedicated asset manager keeping everything visually consistent
- No dedicated prompt engineer: each member writes prompts for their own parts using a fixed five-part structure
They also shared actual prompts and three failure cases with fixes — a rare full first-hand account of embedding AI into a traditional animation pipeline.
More from Multimodal
- Open-source Valen: a visual decision model scoring candidates in 122–128 ms — aigclink · 2026-09-28
- NotebookLM can now generate faceless videos in seconds: 7 prompts to do it all — anthara_ai · 2026-09-28
- One Prompt, Full Lesson: Opus 5.5 Removes the Production Bottleneck in Educational Video — victor_explore · 2026-09-28
- 63 Claude Opus motion graphics videos hit 13M views in a week, all one prompt away — tibo_maker · 2026-09-28
- GPT-6 Astra demo turns real-room video into interactive 3D worlds for robot training — 141_1337 · 2026-09-28
- Quantum Neon Origami: a glowing geometric-fold prompt template for image generation — LudovicCreator · 2026-09-28