HeyGen's first general-purpose video model tops text-to-video blind test
aftahi_ai · x · 2026-10-23
HeyGen announced that its first general-purpose video model, HeyGen Video 1, ranked #1 in text-to-video in a blind test run by Artificial Analysis, beating today's leading video models. A team member noted that landing first place right out of the gate is rare for any team.
More from Multimodal
- Seedance 2.5 demo: a world that lost its colors except one kept behind glass — LudovicCreator · 2026-10-23
- AI video: an orange cat in a parka rides a flying vacuum from the South Pole to the Amazon — legendofketty19 · 2026-10-23
- MOSS Image 5B Base tested: no LoRA, no finetune, straight gens at 50 steps / CFG 3 — Unit2209 · 2026-10-23
- Moss-Image-Edit by chinoll lands on Hugging Face — Slight_Tone_2188 · 2026-10-23
- Underwater fantasy videos with Seedance: a 4-step light, motion-capture workflow — HeyNayeem · 2026-10-23
- World Labs' Atlas builds large 3D worlds from a single image with camera-path video — theworldlabs · 2026-10-23