Yep, however rather than using one large autoregressive model over the entire image, the fractal generative model takes a divide-and-conquer approach. In other words, the model recursively divides the image into patches, and embeds them to form the input
sequence for a
MULTIMODAL AI
-
Fractal Generative Model Uses Divide-and-Conquer Approach
By
–
-
Aria 2 Glasses Excel for Robot Data Collection and Agentic Use
By
–
the Aria 2 glasses are pretty great for robot data collection. they're also getting really good for general agentic use… full details below
-
Agentic Document Extraction: Beyond Traditional OCR
By
–
Announcing: Agentic Document Extraction!
— Andrew Ng (@AndrewYNg) 27 février 2025
PDF files represent information visually – via layout, charts, graphs, etc. – and are more than just text. Unlike traditional OCR and most PDF-to-text approaches, which focus on extracting the text, an agentic approach lets us break a… pic.twitter.com/IdPVahRXL1Announcing: Agentic Document Extraction! PDF files represent information visually – via layout, charts, graphs, etc. – and are more than just text. Unlike traditional OCR and most PDF-to-text approaches, which focus on extracting the text, an agentic approach lets us break a
-
AI Detects Liver Disease from Echocardiogram Scans
By
–
New example of opportunistic A.I. in medicine
Get a liver diagnosis from an echocardiogram https://
ai.nejm.org/doi/full/10.10
56/AIoa2400948
… @NEJM_AI @Yuki_Sahashi @David_Ouyang @CedarsSinai -
Voice Stack Systems Advancing Rapidly for New AI Applications
By
–
The Voice Stack is improving rapidly. Systems that interact with users via speaking and listening will drive many new applications. Over the past year, I’ve been working closely with http://
DeepLearning.AI, AI Fund, and several collaborators on voice-based applications, and I -
Replicate releases Wan 2.1 1.3b faster cheaper video model
By
–
We also released the Wan 2.1 1.3b model (text to video only) yesterday:https://t.co/10eha2PWBg
— Replicate (@replicate) 27 février 2025
This smaller model runs faster and is cheaper, but the coherence takes a bit of a hit compared to 14b. These take about 18s to run at 480p. pic.twitter.com/VzPMFjaXisWe also released the Wan 2.1 1.3b model (text to video only) yesterday: https://
replicate.com/wan-video/wan-
2.1-1.3b
… This smaller model runs faster and is cheaper, but the coherence takes a bit of a hit compared to 14b. These take about 18s to run at 480p. -
Wavespeed Wan 2.1: Experiment with Settings for Realistic Videos
By
–
The Wavespeed Wan 2.1 models also expose a number of different settings for you to experiment with.
— Replicate (@replicate) 27 février 2025
Try experimenting with guide_scale, shift and steps. We've found that a lower scale and shift (about 4 and 2) can give lovely realistic videos. pic.twitter.com/IGXNxdSQa0The Wavespeed Wan 2.1 models also expose a number of different settings for you to experiment with. Try experimenting with guide_scale, shift and steps. We've found that a lower scale and shift (about 4 and 2) can give lovely realistic videos.
-
720p Resolution Now Available for WAN 2.1 Text and Image
By
–
Use 720p if you need a higher resolution.https://t.co/s2mDpUyVz0https://t.co/xkbAB2vFdJ pic.twitter.com/t3wv0tZJSQ
— Replicate (@replicate) 27 février 2025Use 720p if you need a higher resolution. https://
replicate.com/wavespeedai/wa
n-2.1-t2v-720p
… https://
replicate.com/wavespeedai/wa
n-2.1-i2v-720p
… -
WAN 2.1 480p Models: Fast Video Generation with Advanced Physics
By
–
We recommend using the 480p models if you want your videos quickly. Great for experimentation. The 14b model really excels at real world physics, you can push it to do things most other models struggle with.https://t.co/RNz44h7jskhttps://t.co/tQAFS0CCHs pic.twitter.com/0u2vH4aqdu
— Replicate (@replicate) 27 février 2025We recommend using the 480p models if you want your videos quickly. Great for experimentation. The 14b model really excels at real world physics, you can push it to do things most other models struggle with. https://
replicate.com/wavespeedai/wa
n-2.1-t2v-480p
… https://
replicate.com/wavespeedai/wa
n-2.1-i2v-480p
… -
Wan 2.1 14b Open Source Video Model Now Available on Replicate
By
–
Wan 2.1 14b is a state of the art open source video model that's now on Replicate.
— Replicate (@replicate) 27 février 2025
We're using WavespeedAI's optimisations to bring you the fastest generations in the world.
A 5s video takes 39s at 480p, or 150s at 720p.https://t.co/UoLPdtI44d pic.twitter.com/nFtLGhxGkYWan 2.1 14b is a state of the art open source video model that's now on Replicate. We're using WavespeedAI's optimisations to bring you the fastest generations in the world. A 5s video takes 39s at 480p, or 150s at 720p. https://
replicate.com/wavespeedai