Dev ditches MiniMax for open-weights LTX-2.5: AI lip-sync reels at $0.32 each
victor_explore · x · 2026-10-05
Developer victorexplore shares his model selection journey for TenKicks, an app generating AI talking-head reels. He first tried MiniMax H3 but found it produced fake subtitles, nodded without speaking, and moved the camera on its own — so he "fired" it. Switching to open-weights LTX-2.5, his pipeline needs just one face photo, one voice file, and one command: the voice drives the mouth. On a single runpod GPU, 63 seconds of talking renders in 16 minutes, costing $0.32 of GPU time per reel, with no credits or subscription. All 11 demo reels feature AI-generated women with fully synced lip movements.
More from Multimodal
- One Prompt Gets Fable to Generate a 5,000-Year History of China Video — FuSheng_0306 · 2026-10-05
- UniMate Releases 3D Rigged Skeleton Models on Hugging Face, ComfyUI Integration Proposed — RazsterOxzine · 2026-10-05
- Full Making-of Released for AI Music Video 'Close All the Windows' — All Prompts and Orchestration Logs Included — Afinetheorem · 2026-10-05
- OctLLM encodes 3D geometry as explicit octree token sequences without sacrificing language ability — _akhaliq · 2026-10-05
- Gemma 31b 'Grand Horror' + H3 generates atmospheric horror video — jrexthrilla · 2026-10-05
- EditHero: First benchmark for long-horizon part-level 3D editing compares agentic vs non-agentic approaches — _akhaliq · 2026-10-05