Back

Shuvodip Ray

 • 

YouTube • 10m

Researchers at Google DeepMind introduced Semantica, an image-conditioned diffusion model capable of generating images based on the semantics of a conditioning image. The paper explores adapting image generative models to different datasets. Instead of finetuning each model, which is impractical for large-scale models, Semantica uses in-context learning. It is trained on web-scale image pairs, where one random image from a webpage is used to condition the generation of another image from the same page, assuming these images share semantic traits

2 replies3 likes
Replies (2)

More like this

Recommendations from Medial

Image Description
Image Description

Aryan patil

 • 

Monkey Ads • 11m

Train your Ai model for free here 👇 no. Technical skills required to do this. You can train an image,audio,pose models here...

3 replies9 likes
Image Description

Arpan Dholakiya

Hey I am on Medial • 3m

🚀 Hiring for Generative AI Engineer (Remote) 🚀 AI-based SaaS company in the health sector seeks Generative AI Engineer. Requirements: - 1-3 years of experience in Generative AI - Expertise in LLMs and Diffusion Models - Strong foundation in compu

See More
2 replies8 likes
Image Description
Image Description

Chetan Bhosale

Software Engineer | ... • 3m

💡 5 Things You Need to Master for learn for integrating AI into your project 1️⃣ Retrieval-Augmented Generation (RAG): Combine search with AI for precise and context-aware outputs. 2️⃣ Vector Databases: Learn how to store and query embeddings for e

See More
3 replies9 likes
7
Image Description

Three Commas Gang

Building Bharat • 10m

AI solution for marketers and product sellers! Building a webapp for you to just upload product image, and input a prompt and voila!!! You can get studio quality images instantly in any orientation and style possible. Will this work better in subsc

See More
3 replies1 like
Image Description
Image Description

Hawk

 • 

Medial • 7m

Midjourney 6.1 is here! What’s new in V6.1? - More coherent images (arms, legs, hands, bodies, plants, animals, etc) - Much better image quality (reduced pixel artifacts, enhanced textures, skin, 8bit retro, etc) - More precise, detailed, and correc

See More
8 replies18 likes
Image Description

Deep Shah

Ex-Founder | Problem... • 23d

Unlocking Precision in AI-Generated Images with ControlNet in ComfyUI Playing around with ControlNet in ComfyUI, I explored how Canny and Depth ControlNet influence AI-generated images. The results? A fascinating blend of structure and creativity!

See More
1 replies10 likes
Image Description

Uttkarsh Singh

Learning • 9m

📌Another Harvard dropout are killing This time it's Gavin Uberti and Chris Zhu who have created the fastest AI chip in the world beating Nvidia as they say. Their startup name is Etched and their chip name is Sohu Etched says Sohu can achieve ov

See More
2 replies9 likes
1
Anonymous
Image Description

Huge announcement from Meta. Welcome Llama 3.1🔥 This is all you need to know about it: The new models: - The Meta Llama 3.1 family of multilingual large language models (LLMs) is a collection of pre-trained and instruction-tuned generative models

See More
1 replies4 likes
1
Image Description

Payal Manghnani

#uiux designer #free... • 1m

Think China is behind in AI? Think again. Most people believe DeepSeek is China’s only top AI model, but that’s far from the truth. China has **TEN** top-tier models trained from scratch—rivaling Europe's best and even Mistral's biggest model. Me

See More
1 replies5 likes
1

Avinash A

Hey I am on Medial • 22d

🔥 Introducing Mercury Coder – the world’s first diffusion-based language model! 🔥 Unlike traditional AI that predicts words one by one 👉 Mercury Coder starts with noise and gradually refines it into clear, coherent text. 💡 Developed by Inception

See More
0 replies2 likes

Download the medial app to read full posts, comements and news.