


Move the image wherever you paint it! Gen-2's new feature 'Magic Pen Ma Liang” is becoming popular, netizens: Urgent Urgent Urgent Urgent
AI can generate videos, has it developed to this stage? !
Just swipe at a photo to make the selected target move!
It was obviously a stationary truck, but as soon as it was brushed, it immediately started up quickly, even the light and shadow were reproduced perfectly
This photo was originally just a photo of a fire, but now with just a swipe, the flames can rise into the sky, and the heat is coming
If you continue If this continues, it will be difficult to distinguish between photos and actual videos!
This is a brand new function created by Runway for the AI video software Gen-2. Through the operation of painting and brushing, the objects in the image can be made to move, and its degree of realism is no less than that of the magic pen Ma Liang
Although it is just a warm-up of the function, the effect became popular on the Internet as soon as it came out:
Seeing that netizens transformed into anxious kings one by one, they shouted "Wait a minute" I don’t want to give it a try”:
Runway also released more function warm-up effects, let’s take a look
Photos turn into videos, move wherever you point
This new feature of Runway is called Motion Brush (Motion Brush).
As the name suggests, you only need to use this brush to "paint" any objects in the picture to make them move.
Not only can it be a still person, but the movements of the skirt and head are very natural
It can also be a flowing liquid like a waterfall, Even the fog can be restored:
Or a cigarette that has not been extinguished:
The bonfire burning in front of you:
Larger backgrounds can also be made dynamic, and even the light and shadow effects of the picture can be changed, such as rapidly moving dark clouds:
Of course, the above is just a clear statement from Runway. They take the initiative to tell you that they have performed certain processing on the photos.
The following videos without traces of smear are even more There is almost no AI modification in it:
A series of effects exploded, which also resulted in the function not being officially released yet. Netizens can’t wait.
There are a lot of people trying to figure out how this feature is implemented. Some netizens are more concerned about when this feature will be released, hoping to find the link directly on 321 (manual dog head)
You can look forward to it, there is indeed a lot of good news
In addition, Runway has also launched other new features
The recent series of AI generation progress seems to indicate that the field of video generation seems to be about to usher in a technological explosion.
Is AI-generated video really going to rise?
In the past few days, some netizens have discovered a new popular gameplay of Vincentian animation software Animatediff
Just need to combine it with the latest research LCM -LORA, it only takes 7 seconds to generate a 16-frame animated video.
LCM-LORA is the latest AI image generation technology launched by BGI and Hugging Face, which can significantly improve the image generation speed of Stable Diffusion
Among them, LCM (Latent Consistency Models) is based on the image generation technology of Stable Diffusion earlier this year. Recently, OpenAI’s “Consistency Model” proposed a new image generation method that can quickly generate 768×768 high-resolution images.
However, LCM is not compatible with existing models, so Tsinghua University and members of Huopaolian have released a new version of the LCM-LORA model, which is compatible with all Stable Diffusion models and speeds up the drawing speed.
Combined with the Animatediff software, it only takes about 7 seconds to generate such an animation:
Currently LCM-LORA Already open sourced on Hughuoxiang.
How do you feel about the recent progress of AI video generation, and how far is it from being usable?
Reference link:
[1]https://twitter.com/runwayml/status/1723033256067489937.
[2]https://twitter.com/op7418/status/1723016460220735748.
The above is the detailed content of Move the image wherever you paint it! Gen-2's new feature 'Magic Pen Ma Liang” is becoming popular, netizens: Urgent Urgent Urgent Urgent. For more information, please follow other related articles on the PHP Chinese website!

Hot AI Tools

Undresser.AI Undress
AI-powered app for creating realistic nude photos

AI Clothes Remover
Online AI tool for removing clothes from photos.

Undress AI Tool
Undress images for free

Clothoff.io
AI clothes remover

Video Face Swap
Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Article

Hot Tools

Notepad++7.3.1
Easy-to-use and free code editor

SublimeText3 Chinese version
Chinese version, very easy to use

Zend Studio 13.0.1
Powerful PHP integrated development environment

Dreamweaver CS6
Visual web development tools

SublimeText3 Mac version
God-level code editing software (SublimeText3)

Hot Topics

The article reviews top AI art generators, discussing their features, suitability for creative projects, and value. It highlights Midjourney as the best value for professionals and recommends DALL-E 2 for high-quality, customizable art.

ChatGPT 4 is currently available and widely used, demonstrating significant improvements in understanding context and generating coherent responses compared to its predecessors like ChatGPT 3.5. Future developments may include more personalized interactions and real-time data processing capabilities, further enhancing its potential for various applications.

Meta's Llama 3.2: A Leap Forward in Multimodal and Mobile AI Meta recently unveiled Llama 3.2, a significant advancement in AI featuring powerful vision capabilities and lightweight text models optimized for mobile devices. Building on the success o

The article compares top AI chatbots like ChatGPT, Gemini, and Claude, focusing on their unique features, customization options, and performance in natural language processing and reliability.

The article discusses top AI writing assistants like Grammarly, Jasper, Copy.ai, Writesonic, and Rytr, focusing on their unique features for content creation. It argues that Jasper excels in SEO optimization, while AI tools help maintain tone consist

Falcon 3: A Revolutionary Open-Source Large Language Model Falcon 3, the latest iteration in the acclaimed Falcon series of LLMs, represents a significant advancement in AI technology. Developed by the Technology Innovation Institute (TII), this open

2024 witnessed a shift from simply using LLMs for content generation to understanding their inner workings. This exploration led to the discovery of AI Agents – autonomous systems handling tasks and decisions with minimal human intervention. Buildin

The article reviews top AI voice generators like Google Cloud, Amazon Polly, Microsoft Azure, IBM Watson, and Descript, focusing on their features, voice quality, and suitability for different needs.
