AI-made star IP car ads cut production from 2 months to 2 weeks using ByteDance Seedance and AMD compute
机器之心 · wechat · 2026-09-18
A three-way collaboration between AMD, ByteDance Volcano Engine, and agency A.M.A produced a series of star IP car ads for the 2026 World Cup using Seedance 2.0/2.5 instead of live shoots.
- Model side: Seedance delivers high-resolution, high-color-depth output, mixed text/image/audio generation, and white-model video anchoring for product structure, with version tiers for different budgets and improved one-shot success rates.
- Agency side: A.M.A built a canvas-based AIGC platform with pluggable Seedance nodes, dozens-to-hundreds of concurrent generation tasks, and reusable asset/skill libraries.
- Compute side: AMD provides cost-optimized inference capacity.
Results: million-yuan-scale star TVCs produced at far lower cost, timelines cut from 2 months to under 2 weeks, throughput up several-fold to over 10x, with quick scene swaps enabling rapid iterations.
More from Multimodal
- Prompt share: 'Digital Fracture' glitch-art template for image generation — azed_ai · 2026-09-18
- LightOnOCR-2-1B: 1B OCR model beats rivals 9x its size, 493K pages/day on one GPU — thisguyknowsai · 2026-09-18
- 2D animations in 15s: full GPT spritesheet + H3 Max Magnific workflow shared — techhalla · 2026-09-18
- KITScenes Multimodal Dataset Launches to Fill the Data Gap for 3D Foundation Models — abursuc · 2026-09-18
- Qwen-Image-2.1 specs leak: 7B DiT, Qwen3-8B encoder, 56GB VRAM for 4K — bdsqlsz · 2026-09-18
- Recreating videos in MiniMax H3: a 4-step frame-extraction workflow — Negative-Whereas3307 · 2026-09-18