Just In: Major AI Video Update! Taking on Sora — Will Smith Eating Noodles Looks Even Better

Just In: Major AI Video Update! Taking on Sora — Will Smith Eating Noodles Looks Even Better

Veo 3.1: Google’s Major Leap in AI Video Generation

Recently, OpenAI launched its Sora 2 model with great momentum. Now, Google has followed up with a powerful upgrade to Veo 3.1 — setting the stage for the next level of AI-generated video.

---

Key Upgrade Areas

1. Enhanced Functionality

  • Advanced Video Editing: Finer control over individual clips, allowing precise adjustments to visuals.
  • New Audio Capabilities: Audio is now integrated into Ingredients to Video, Frames to Video, and Extend features — expanding creative possibilities.

image

---

2. Model Advancements

  • Better Prompt Understanding: Improved interpretation of complex creative instructions.
  • Higher Audiovisual Quality: More natural conversion from still images to animated scenes.

Related reading: The New AI Video Leader Goes Viral Worldwide — Will Smith Finally Eats in Peace (includes real-world demos).

image

---

Building on Veo 3’s Editing Power

Veo 3 already supported:

  • Editing via reference images
  • Filling in missing frames between start and end shots
  • Extending videos beyond original end points

Now, Veo 3.1 adds audio to all these tools — making scenes richer and more complete.

These audio features are currently experimental, with Google planning iterative improvements based on feedback.

image

---

How to Use the New Features

  • Ingredients to Video
  • Supply multiple reference images for characters, objects, and styles — Veo generates the final scene accordingly.
  • Frames to Video
  • Provide start and end frames, and Veo fills in transitional frames for smooth scene progressions.
image
image
  • Extend
  • Create videos beyond one minute — Veo continues from the last frame while keeping narrative flow.
image

---

Format Versatility

  • Before: Only 720p landscape output
  • Now: Supports 16:9 landscape and portrait modes — matching today’s vertical-first social trends.

---

New Editing Tools in Flow

Flow has generated 275 million+ videos since May. Based on user feedback, two new features were added:

  • Insert New Elements – Add objects anytime; lighting and shadows auto-adjust for realism.
  • Remove Objects (coming soon) – Delete unwanted elements and auto-reconstruct the background.

These upgrades make iterative post-production far more flexible.

---

Why It Matters for Creators

Platforms like Veo 3.1 and Flow offer unprecedented creative control and speed.

For efficient cross-platform publishing and monetization, open-source ecosystems like AiToEarn integrate:

  • AI content generation
  • Multi-platform publishing (Douyin, Kwai, WeChat, Bilibili, Rednote, Facebook, Instagram, YouTube, X)
  • Analytics & AI model rankings

Documentation | GitHub

image

---

Accessing Veo 3.1

  • Developers: Gemini API
  • Enterprise: Vertex AI
  • Everyone: Gemini app

image

---

Real-World Applications

  • FPV flythrough
  • ASMR fruit slicing
  • Nocturnal surveillance (metal structure, rabbits, trampoline)

image

---

Example: Glass Lemon Scene

Veo 3.1 captured “melting glitter” details with far better precision than Veo 3.

image

---

Example: E-commerce Product Video

Sora 2 added thoughtful Chinese voice narration.

Veo 3.1 delivered superior visual fidelity — commercially polished output.

image

image

---

Example: Anime Style

Performance in stylistic animation remains average, with occasional glitches (e.g., missing dog).

image

image

---

Will Smith Eating Noodles Test

Shared by @aisearchio — improvement seen in:

  • Motion smoothness
  • Light & shadow detail
  • More expressive faces without breaking realism

image

---

Final Thoughts

  • Photorealistic & Commercial-Grade: Veo 3.1 delivers usable outputs for professional work.
  • Stylistic Gaps: Anime/illustration needs stronger constraint handling.
  • Rapid Iteration: AI video generation is evolving faster than most expected.

As tools like Veo and Sora move towards mainstream mass consumption, expect AI-generated content to increasingly dominate your feeds.

Verification of authenticity will become an essential habit.

For navigating this space, solutions like AiToEarn官网 offer integrated generation, cross-platform distribution, and monetization — helping creators thrive amid widespread AI content production.

📎 Video link: https://mp.weixin.qq.com/s/qBOkoWaGF5k7oPCR_H5aqA

Read more

Google DeepMind Launches CodeMender: An Intelligent Agent for Automatic Code Repair

Google DeepMind Launches CodeMender: An Intelligent Agent for Automatic Code Repair

Google DeepMind Launches CodeMender — AI for Automated Software Vulnerability Repair Date: 2025-10-18 13:09 Beijing --- Introduction Google DeepMind has unveiled CodeMender, an AI-powered intelligent agent designed to automatically detect, fix, and strengthen software vulnerabilities. Built on cutting-edge reasoning models and program analysis technologies, CodeMender aims to dramatically cut the

By Honghao Wang
What Signal Is Behind People’s Daily’s Consecutive Interviews with Entrepreneurs?

What Signal Is Behind People’s Daily’s Consecutive Interviews with Entrepreneurs?

Anti-Overcompetition — Urgent Action Needed! --- Source: Reprinted from the WeChat public account 笔记侠PPE书院 (bijixiafuwu) (authorized). Contact the original publisher for permission before reprinting. Article stats: 9,929th in-depth piece | 5,625 words | ~16 min read --- Understanding Overcompetition (Involution) Editor’s note: Overcompetition (内卷) is now a serious concern in

By Honghao Wang