GPT-6 Astra turns text prompts and a reference image into Blender 3D modeling
petewoodbridge · x · 2026-09-18
A demo shared by fal shows GPT-6 Astra making Blender 3D modeling and animation as simple as a text prompt with a reference image. Professional creatives are using 3D video to guide video models like H3 Max. Full video on YouTube.
More from Multimodal
- Creator builds StyleGAN dataset from ~3,000 synthetic JAX diffusion images — makeitrad1 · 2026-09-18
- Can Local Music Model Yue2 Do True Reference2Audio? Community Asks — Ambitious_Fold_2874 · 2026-09-18
- Pika relaunches as all-in-one AI creative platform aggregating Seedance, Nano Banana and more — Kyrannio · 2026-09-18
- What if you could swap bodies with someone for one hour a day? AI video goes viral — Weak-Abalone-9647 · 2026-09-18
- Claude picked the Voynich Manuscript, failed to crack it, then made a surprisingly good explainer video — emollick · 2026-09-18
- MiniMax-H3 in Practice: 10s 1MP Clips in Under 6 Minutes on a 5070Ti — Sleepy_Bandit · 2026-09-18