How much longer until AI is completely undistinguishable from reality? I say 6 months

Coherent character: Shot by shot technique
Complete workflow 👇 👇👇

This AI tool is just amazing.

Twin AI creates stunning videos while keeping your product details, subject, and background consistent.

Here's how ⤵️

From sketch to this using the new conversational editing workflow with Chatgpt. 🤯

We're so cooked.

This is Reve Image 1.0, the best AI image model in the world.

There is no way to tell anymore...

Here are 10 insane examples:

Google Veo-2 is currently the best AI video generator out there.

3D AI is getting crazier

this new Hunyuan3D 2.0 MV open source model can generate 3D asset with multiple images in seconds 

free to use now, link in comments

10 examples:

Let AI Create, Post, and Sell for You 24/7

we’ve built the most natural lipsync model in the world.

again.

this new AI video generator is crazy..

Twin AI can keep the actor, outfit, background, and even tiny product detail consistent simultaneously and..

even lip-sync external video and train any voice

step by step tutorial:

SpatialLM just dropped on Hugging Face

Large Language Model for Spatial Understanding

WanVideo W&Bmanga LoRA v2v 変換 test(beta)

This is so cool!

Google Gemini 2.0 Flash can edit images in any style.

I asked it to add a man to a sketch, and it did so well without deviating from the style!

this all in one AI platform is incredible 

you can use all the top AI video generators like Veo 2, Kling,  Runway, Hunyuan on Pollo AI and.. 

create consistent character, lip-sync, upscaler, face swap and more all in one place

10 examples:

Insert products in photos without lora training

Here's how to use it:
#aipartner

Alright, Google really killed it here.

You can easily swap your garment just by uploading the pieces to Gemini Flash 2.0 and telling it what to do.

Wan 2.1 (1.3bn) text-2-video

Flat Color Lora

Control Lora Depth

🥵🥵🥵🥵

Revid AI - Ideate, Publish, Go Viral | #1 AI Video Generator

This is crazy!

How can anyone say that AI video generation is not the future?

I wouldn't have dreamt of doing this last year, and I was an optimist.

By the end of the year, it'll become the norm.

Made with @GoogleDeepMind Whisk and @LumaLabsAI 

1.

“Midjourney killer”
“We’re cooked”
“Game changer”
“This is crazy”

Lots of things are being said about Reve… I will say it’s cinematic AF!!

A quick montage:

new video unlocks are unreal

completely AI generated

🛠️ Blender MCP update:

Bring in high-quality assets to Blender through just  prompts, thanks to an integration with @polyhaven’s library of 1500+ assets.

Watch me create a beachy scene with just words. (Watch how it imports the right HDRIs, textures and models) 👇

AI is ready to make some films..

I've been testing this incredible Twin AI video studio, it can keep the character, outfit and background consistent and..

it's lip syncing is so human like and realistic 

step by step tutorial:

Our newest AI Short Film “PAPER JAM”! 

Each keyframe was animated by hand based on AI generated 3D models. "Rendered" using Flux + regional Loras in ComfyUI and interpolated using @Kling_ai

A billion-parameter voice AI is now open source

Sesame AI just dropped CSM-1B -  the voice engine behind its viral assistant Maya.

- Fully open.
- Apache 2.0 license.
- No paywalls. No permission needed.

Here's everything you need to know:

Hand-Drawn to Video:

Image to Image – ChatGPT 4o
 
Prompt: Create a comical story strip from the hand-drawn image (you can define the animation style)

Image to Video – Hailuo AI

Additional Images in the reply!

Meta just dropped a new paper.

"A Recipe for Generating 3D Worlds From a Single Image"

Turn a single image into a high-quality 3D world ready for VR.

10 wild examples:

Honestly, Runway first frame has more range than I initially thought. I will say they could really use a green screen button to replace the backgrounds though.