Fable 5.2's first autonomous cut: a 3m33s video with a bad song choice
FinanceYF5 · x · 2026-11-10
The first cut of the "make a video of your dreams" experiment with Fable 5.2: the model produced the entire 3m33s video autonomously, but picked a bad song and its voice mode broke at the start. After fixes, the final 4-minute version took 9 hours total, with all scenes drawn as SVG in code before video generation.
Related event: Fable 5.2 Autonomously Creates Full Video From a Single Prompt(3 posts)→
More from Multimodal
- Is ControlNet Obsolete? New DiT Image Models Ship Without It — Manicarus · 2026-11-10
- Full prompt revealed: how to recreate the Van Gogh convenience store in MiniMax H3 Image — mhdfaran · 2026-11-10
- 10 open-source GitHub repos for voice AI: from local ASR to zero-shot voice cloning — Shruti_0810 · 2026-11-10
- Fable 5.2 generates animated nature scene with ~70k trees from one prompt — Merzmensch · 2026-11-10
- MOSS-Image roundup: Control LoRAs, 461 new characters, and 20-minute LoRA training on a 5090 — optimisticalish · 2026-11-10
- StreamEval from Tsinghua, NVIDIA, CMU and Berkeley exposes gaps in streaming video generation across 38 models — jiqizhixin · 2026-11-10