113043
The largest AI art gallery on Telegram! Ads: @CaptainJamesCook
This is 'Mind Tunnels.' Made entirely with Gen AI.
Welcome to the new era of filmmaking!
Robots & Art 🐐
Someone created an AI video “interviewing” people from the 1500s and it’s hilarious
Robots & Art 🐐
Luma Labs dropped Modify Video, a tool to restyle videos by changing style, settings, and more
In blind tests, it outperformed Runway V2V across key criteria, retaining motion, facial animation, and temporal consistency
Available in Dream Machine: Ray 2
Robots & Art 🐐
Midjourney v7 -> Veo 3 on FLOW
Static shot of an underwater coral reef
Robots & Art 🐐
Google's Veo3 is insane
Robots & Art 🐐
Tencent launched HunyuanVideo-Avatar, a new AI video model
It turns a single reference image and audio into a realistic short video with lifelike speech/singing
Suitable for domains like ecommerce and advertising
Robots & Art 🐐
5000 years of hairstyle evolution seen by AI
Robots & Art 🐐
AI video evolution: 2023 → 2025
Robots & Art 🐐
This tech (Veo 3) is too good to be true.
Robots & Art 🐐
Created with Google Flow.
Visuals, Sound Design, and Voice were prompted using Veo 3 text-to-video.
Welcome to a new era of filmmaking.
Robots & Art 🐐
Self-aware AI characters made with Veo 3
Robots & Art 🐐
We live in the golden age of comedy, there's no doubt about that. Veo 3 enables us to do crazy things.
The Adventures of Slop-Man:
Robots & Art 🐐
This is how potato chips are made
Robots & Art 🐐
Bigfoot vloggin by veo3
Robots & Art 🐐
Next level drama by Veo3
Robots & Art 🐐
Lmao. What niche even is this — grassroots dirt track racing meets google maps nerds?
Veo 3 videos are seriously ridiculous and fun.
Robots & Art 🐐
This is 100 % AI, Veo 3
Robots & Art 🐐
Midjourney -> Kling 2.1 pro
Robots & Art 🐐
Google Veo 3 // Suno v4.5
Robots & Art 🐐
Flux launched a new model Flux Kontext
> Character consistency is SOLVED
> You can also do precise editing with prompt
It's reportedly better than Gemini native image and GPT-4o image.
Robots & Art 🐐
Afterlife: The unseen lives of AI actors between prompts. (Made with Veo 3)
Robots & Art 🐐
Tencent's Hunyuan team open-sourced its HunyuanPortrait model
Based on Stable Video Diffusion, this AI uses video templates to turn static reference images into lifelike, temporally consistent portrait animations
Robots & Art 🐐
This video was made using Veo3. Took just 45 minutes and cost $33 total.
Prompt:
2000s TV show, broadcast booth. A man, Mike, around 35 years old, is sitting and speaking from a broadcast booth. He’s wearing an earpiece and talking to the camera with an energetic voice. With humor, he says: “This is SmackDash… and these guys are going to have a blast… literally!”
Veo 3 can generate music too...
Robots & Art 🐐
Kling 2.1 Pro generates 1080p results fast and cheaper than Kling 2.0:
Midjourney v7 -> Kling 2.1 Pro
Robots & Art 🐐
Three years of progress in AI
1. Midjourney in July 2022
2. Veo 3 in May 2025
Robots & Art 🐐
Live action Ratatouille, thanks to Veo3
Robots & Art 🐐
By the end of this year, most short-form content on platforms like TikTok will probably be AI-generated. This video is 100% AI made with Veo 3.
Robots & Art 🐐
Generated by Veo 3
Robots & Art 🐐