AI Speed Box

AI News and Information Link Collection (Mint Bear's ignorant SNS scraps, matured to become Visual AI News)
2025 AI Era Human Intelligence Conference
  1. AI
 
 
2025/01/12
Limited Release (Partial Release)
Voice Cursor
  1. AI Sound
  1. ETC sound
 
 
 
 
2024/12/22
Available Now (Available)
Photoshop (Beta) New Feature: Select Body Parts
  1. AI Image
  1. Adobe Photoshop
 
 
 
 
2024/12/19
Available Now (Available)
Report: AIBRAHAM
Kling 1.6
  1. AI Video
  1. Kling
 
 
 
 
2024/12/19
Available Now (Available)
Ideogram Batch Generation
  1. AI Image
  1. Ideogram
 
2024/12/18
Available Now (Available)
Midjourney Office Hours (2024-12-18)
  1. AI Image
  1. Midjourney
 
 
2024/12/18
Coming Soon
Veo 2
  1. AI Video
  1. _Google
 
 
 
 
2024/12/17
Coming Soon
Midjourney Moodboards
  1. AI Image
  1. Midjourney
2024/12/17
Available Now (Available)
Google's New AI Glasses (Android XR)
  1. AR, XR, VR
  1. _Google
 
 
2024/12/16
Coming Soon
Video watermarking technology, Meta Video Seal
  1. AI Video
  1. _Meta
 
 
 
 
2024/12/15
Available Now (Available)
Pika 2.0 Update
  1. AI Video
  1. Pika
 
 
 
2024/12/15
Available Now (Available)
Motivo by Meta
  1. AI 3D
  1. _Meta
 
 
 
2024/12/15
Available Now (Available)
Leffa by Meta
  1. AI Image
  1. _Meta
 
 
 
2024/12/14
Available Now (Available)
The Gemini 2.0
  1. AI LLM
  1. Genmini
 
 
 
 
2024/12/13
Limited Release (Partial Release)
Krea Editor Updates
  1. AI Image
  1. Krea
 
 
2024/12/13
Trellis Trellis 3D
  1. AI 3D
  1. 3D
 
 
2024/12/12
Available Now (Available)
Rodin
  1. AI 3D
  1. ETC
 
 
2024/12/12
Available Now (Available)
Midjourney Patchwork
  1. AI Image
  1. Midjourney
 
 
2024/12/12
Available Now (Available)
DiffSensei
  1. AI Toons
  1. ETC toons
 
 
 
 
2024/12/11
Available Now (Available)
MMAudio: Video-to-Audio Synthesis
  1. AI Sound
  1. ETC sound
 
 
 
 
2024/12/11
Available Now (Available)
Sora v2 showing in London
  1. AI Video
  1. Sora
 
 
 
2024/12/09
Available Now (Available)
Leonardo - FlowState
  1. AI Image
  1. Leonardo
 
 
 
 
2024/12/07
Available Now (Available)
ElevenLabs _ Conversational AI
  1. AI Sound
  1. ElevenLabs
 
 
2024/12/06
Coming Soon
Open AI, 12 days of live
  1. AI
  1. OpenAI
  2. OpenAI o1
  3. Sora
 
 
2024/12/05
Limited Release (Partial Release)
Google DeepMind just dropped Genie 2
  1. AI Video
 
 
 
2024/12/05
Available Now (Available)
Swift-Edit
  1. AI Image
  1. ETC Image
 
 
 
2024/12/05
Available Now (Available)
Midjourney Office Hours (2024-12-04)
  1. AI Image
  1. Midjourney
 
 
2024/12/04
Coming Soon
Gen3 KeyFraming (Prototype)
  1. AI Video
  1. Gen-3
Preview of the ability to organically create images and videos from a blank canvas
https://runwayml.com/research/creativity-as-search-mapping-latent-space
2024/12/03
Coming Soon
Hunyuan Video by Tencent
  1. AI Video
  2. AI Sound
  1. Hunyuan
 
 
 
 
2024/12/03
Available Now (Available)
Motion Prompting (Google DeepMind)
  1. AI Video
  1. _Google
 
 
 
 
2024/12/03
Coming Soon

Gen3 KeyFraming (Prototype)

Category
  1. AI Video
Gen
  1. Gen-3
Date
2024/12/03
Summary 🍀🧸
Preview of the ability to organically create images and videos from a blank canvas
URL
https://runwayml.com/research/creativity-as-search-mapping-latent-space
Release
Coming Soon

Gen-3 KeyFraming (Prototype)

( X Posting Expert )
Today we share an early video keyframing prototype that treats creative exploration as a process of exploration of all potential artistic possibilities, allowing us to simultaneously explore this vast space with precise control and serendipitous nonlinear discovery.

Graph Structure: A Window into the Latent Space

The graph structure is the basis of the prototype. Images are represented as nodes, which act as waypoints in the latent space of the model. These nodes can be connected to other nodes to create edges. Edges are video transitions from the first frame to the last frame through latent space and time.

Balance of control and chance

Precise control helps to limit the vast space of possibilities, but at the same time, variation and unpredictability can lead to “happy accidents” – possibilities that would not have been considered if precise control had been given. To strike this balance, we provide two possibilities for the user to manipulate the image in a “relational” way that allows for unpredictability in a consistent dimension.
Users can transform a selected image via “Image to Image,” which changes the style via text prompts while preserving the original composition, while “Transform Image” changes the composition while maintaining the original style.

Nonlinear search support

Creative exploration rarely follows a straight line. Graph structures naturally encourage exploration by allowing users to branch off at various points, creating new forks of possible alternatives. As more exploration occurs, the graph naturally grows, tracing different paths of experimentation.
This allows users to construct non-linear timelines. We provide a sequencer that allows users to export non-linear timelines as videos with linear timelines, similar to a “choose your own adventure” experience.

Open workspace

Beyond the graph structure, we do not impose any organizational constraints on the workspace. Users have complete freedom to organize nodes and edges, cluster related explorations according to their process needs, or isolate unique creative experiments.
👍