John Steward

HDiffusion's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

upvoted 3 papers 5 months ago

PowerInfer-2: Fast Large Language Model Inference on a Smartphone

Paper • 2406.06282 • Published Jun 10 • 36

Guiding a Diffusion Model with a Bad Version of Itself

Paper • 2406.02507 • Published Jun 4 • 15

Phased Consistency Model

Paper • 2405.18407 • Published May 28 • 46

upvoted a collection 7 months ago

Kohaku XL

Collection

Kohaku series SDXL anime base model • 9 items • Updated Sep 29 • 7

upvoted 4 papers 7 months ago

Diffusion-RWKV: Scaling RWKV-Like Architectures for Diffusion Models

Paper • 2404.04478 • Published Apr 6 • 12

No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance

Paper • 2404.04125 • Published Apr 4 • 27

Bigger is not Always Better: Scaling Properties of Latent Diffusion Models

Paper • 2404.01367 • Published Apr 1 • 20

Getting it Right: Improving Spatial Consistency in Text-to-Image Models

Paper • 2404.01197 • Published Apr 1 • 30

upvoted 3 papers 8 months ago

ViTAR: Vision Transformer with Any Resolution

Paper • 2403.18361 • Published Mar 27 • 52

GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation

Paper • 2403.12365 • Published Mar 19 • 10

Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation

Paper • 2403.12015 • Published Mar 18 • 64

upvoted 3 papers 9 months ago

The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Paper • 2402.17764 • Published Feb 27 • 602

SDXL-Lightning: Progressive Adversarial Diffusion Distillation

Paper • 2402.13929 • Published Feb 21 • 27

Neural Network Diffusion

Paper • 2402.13144 • Published Feb 20 • 94

upvoted 6 papers 10 months ago

MambaByte: Token-free Selective State Space Model

Paper • 2401.13660 • Published Jan 24 • 50

Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers

Paper • 2401.11605 • Published Jan 21 • 21

A Shocking Amount of the Web is Machine Translated: Insights from Multi-Way Parallelism

Paper • 2401.05749 • Published Jan 11 • 6

ANIM-400K: A Large-Scale Dataset for Automated End-To-End Dubbing of Video

Paper • 2401.05314 • Published Jan 10 • 9

MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts

Paper • 2401.04081 • Published Jan 8 • 70

Mixtral of Experts

Paper • 2401.04088 • Published Jan 8 • 157