I Tried Every New Veo 3.1 Trick - Wow

I Tried Every New Veo 3.1 Trick - Wow

by Matt Wolfe

Applied Sciences & Engineering AI — Models & Research UYQArtificial intelligence (AI)UYQFGenerative artificial intelligence
🎙 Matt Wolfe 👥 1.0M 📅 October 18, 2025 ⏱ 25 min 👁 95K 📄 expert opinion 🧭 2026-08-28
Available in: English (current) Français

Keywords

Veo 3.1Google FlowAI video generationSora 2features

Summary

Matt Wolfe presents a comprehensive overview and hands-on test of Google’s Veo 3.1 video generation model. He outlines the new features: ingredients to video (combining multiple reference images), frames to video (animating between two frames), video extension, and new editing capabilities (adding objects, though removal is not yet available). He demonstrates each feature within Google’s Flow platform, comparing results with OpenAI’s Sora 2. The video includes a sponsored segment for Warp, a coding tool. Key observations include that Veo 3.1 allows generation of trademarked characters (Mickey Mouse, Mario, Batman) while Sora 2 now refuses, and that Sora 2 generally produces more realistic videos and better physics, while Veo 3.1 offers more editing control. The creator concludes that Sora 2 is slightly more impressive out-of-the-box, but Veo 3.1’s editing features are valuable for iterating towards desired results. He also notes that the ‘ingredients to video’ feature is only available on the ‘fast’ model, not the ‘quality’ model.

156 words

Critical Evaluation

Value of the Information & Strength of the Argument

The video provides valuable, hands-on information about Veo 3.1’s new features, including practical tips (e.g., ingredients to video only on fast model) and honest comparisons with Sora 2. The argumentation is based on direct testing and personal experience, which is appropriate for an opinion piece. The creator clearly states his biases (adviser for Leonardo) and acknowledges limitations (e.g., not an apples-to-apples comparison). The reasoning is coherent and well-structured, moving from feature overview to testing to final thoughts.

Scientific Rigor, Source Quality, Title Accuracy

The video is a practical demonstration and opinion piece, not a scientific review. The creator does not cite external sources, but relies on his own testing and observations. The title accurately reflects the content. The description includes links to his own platform (futuretools.io) and social media, but no direct references to Google’s official documentation or research papers. The creator’s credibility as an AI tools reviewer is established through his channel and community. The video’s scientific rigor is moderate, appropriate for its format.

174 words

Title / Content Match

The title accurately reflects the content: the creator tests and demonstrates various new features of Veo 3.1, expressing surprise and amusement at the results.

Quality & Reliability

7/10

The video is a hands-on demonstration and opinion piece by a known AI tools reviewer. It clearly separates factual feature announcements from personal testing and opinions. The creator discloses a potential bias (adviser for Leonardo). No formal citations or sources are provided beyond the creator's own platform and social links.

Chapters

Cited Sources

  • FutureTools.io — Creator's platform for AI tools and news, mentioned in the video and description.
  • FutureTools Newsletter — Creator's newsletter, mentioned in the video and description.
  • Warp (sponsor) — Sponsor link for Warp, a coding tool, mentioned in the video's sponsored segment.
  • Matt Wolfe on LinkedIn — Creator's LinkedIn profile, listed in the description.
  • Matt Wolfe on Threads — Creator's Threads profile, listed in the description.

Concurring Sources

Dissenting Sources

  • OpenAI Sora — The video compares Veo 3.1 with Sora 2, noting differences in content policy and output quality, which may be seen as discordant from a purely comparative perspective.

Contribution & Novelties

The video offers a practical, user-centric evaluation of Veo 3.1’s new features, highlighting its strengths (editing capabilities, lenient content policy) and weaknesses (physics, initial generation quality) compared to Sora 2. It provides a timely, hands-on perspective that complements official announcements.

Pour aller plus loin :

  • Google Veo 3.1 official page — Official information on Veo 3.1 features and capabilities.
  • OpenAI Sora — Official page for Sora, the main competitor discussed.
  • Google Flow — The platform used for testing Veo 3.1, as mentioned in the video.
  • Leonardo AI — A third-party platform that offers Veo integration, mentioned as a cost-effective option.

100 words

Radar Profile

The radar profile shows high scores in information quantity and quality, reflecting the video's comprehensive coverage and practical demonstrations. The technical level is moderate, suitable for a general audience interested in AI tools. The overall reliability is good, given the creator's experience and transparent testing, though it is based on personal opinion rather than formal research.

Reliability 7/10

💬 Positif. Sur les 30 commentaires analysés, le public est très enthousiaste, appréciant les démonstrations humoristiques et les comparaisons, avec quelques remarques techniques sur les fonctionnalités et les différences avec Sora 2.