Testing Fable 5.2 image model: creator shows off results made for 1 token
alex_verem · x · 2026-11-10
The author tested the Fable 5.2 image generation model for just 1 token and shared the craziest images they created with it — an early hands-on demo of a new generative model.
More from Multimodal
- MiniMax teases upcoming H3-Image generation model — victormustar · 2026-11-10
- Dev builds vocal synth modeling the vocal tract as branching acoustic tubes, not phoneme stitching — TinfoilTricorn · 2026-11-10
- Open-source RGBMocap adds live mocap streaming into Blender with motion baking — camenduru · 2026-11-10
- Local MiniMax H3 on 6GB VRAM recreates Harry Potter scene at ~50 min per image — No_Cow26 · 2026-11-10
- 3D celebrity caricature prompt shared: exaggerated head, recognizable face — azed_ai · 2026-11-10
- Agent given a vocal-synth repo builds branching acoustic-tube singing synthesis — TinfoilTricorn · 2026-11-10