Stories by GaggiX

No positional encoding outperforms all positional encoding variants in decoders

Ghost in the Minecraft: Generally Capable Agents for Open-World Enviroments

Training Diffusion Models with Reinforcement Learning

Key-Locked Rank One Editing for Text-to-Image Personalization

In-Context Learning Unlocked for Diffusion Models

Text-to-Audio Generation Using Instruction Tuned LLM and Latent Diffusion Model

Training Stable Diffusion from Scratch for <$50k with MosaicML

MiniGPT-4

A new Paella: simple and efficient text-to-image generation

ControlNet v1.1

GeNVS: Generative Novel View Synthesis with 3D-Aware Diffusion Models

Taming Encoder for Zero Fine-Tuning Image Customization

SuTI: Subject-Driven Text-to-Image Generation via Apprenticeship Learning

Generative Artificial Intelligence Chatbots Have Risen to Human-Level Creativity

Token Merging for Fast Stable Diffusion

LLaMA-Adapter: Efficient Fine-Tuning of LLaMA

Donald Trump Shares Fake AI-Created Image of Himself on Truth Social

Zero-1-to-3: Zero-shot One Image to 3D Object

Privacy vulnerability in the Google Pixel's inbuilt screenshot editing tool

1
2
3
4
5