Spira Maxima 1.0 turns plain text into ready-to-post social videos
hey_abusiddik · x · 2026-10-07
Spira Labs launched Spira Maxima 1.0, pitched as the most complete text-to-social-video model: plain text becomes a finished social video with a presenter, on-trend B-roll, transitions, captions and music, ready to post.
Its key differentiator is post-training: the model is trained on trending videos and performance data, so generations supposedly follow what currently works on the feed. The team claims thousands of videos generated on launch day and a #1 spot, and promises to open-source it once the post hits 2M views or the account reaches 5K followers.
Related event: Spira Maxima 1.0: Text-to-Finished Social Video Model Released(4 posts)→
More from Multimodal
- Mirage's Tesseract + Opus 5.5 generated its entire launch video, exported to After Effects — aziz4ai · 2026-10-07
- Nano Banana 2.1 vs Midjourney 8.2: same-prompt image comparison surfaces — miilesus · 2026-10-07
- A lot of AI slop films are just porn, observer points out — moonsandhues · 2026-10-07
- First AI-Made Film Gets Traditional Theatrical Run, Submits for Best Animated Feature Oscar — Uncanny_Harry · 2026-10-07
- AI turns kids' doodles into fluffy living creatures — horned tiger included — anthara_ai · 2026-10-07
- Seedance 2.5 AI video of Dragon Ball battle wows with detail and motion — anthara_ai · 2026-10-07