Zijian Zhou PRO

franciszzj's activity

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

upvoted 2 papers 4 days ago

MoCha: Towards Movie-Grade Talking Character Synthesis

Paper • 2503.23307 • Published 7 days ago • 85

TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes

Paper • 2503.23461 • Published 6 days ago • 85

upvoted a collection 14 days ago

FLUX.1

Collection

A collection of our FLUX.1 models and LoRAs. • 8 items • Updated Jan 31 • 53

liked a model 18 days ago

stabilityai/stable-virtual-camera

Image-to-Video • Updated 17 days ago • 17.5k • 162

upvoted a paper 24 days ago

VACE: All-in-One Video Creation and Editing

Paper • 2503.07598 • Published 26 days ago • 43

upvoted a paper 27 days ago

EgoLife: Towards Egocentric Life Assistant

Paper • 2503.03803 • Published Mar 5 • 38

upvoted 3 papers about 1 month ago

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning

Paper • 2502.19634 • Published Feb 26 • 62

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Paper • 2502.14786 • Published Feb 20 • 139

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published Feb 19 • 178

liked a Space about 2 months ago

Running on Zero

49

49

Diffusion Eraser

🌍

Generate images from text prompts

liked 2 models 2 months ago

deepseek-ai/Janus-Pro-1B

Any-to-Any • Updated Feb 1 • 37.3k • 416

deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated Feb 1 • 286k • 3.29k

liked 2 Spaces 2 months ago

Running on Zero

1.93k

1.93k

Chat With Janus-Pro-7B

🌍

A unified multimodal understanding and generation model.

Running on Zero

208

208

JanusFlow 1.3B

🏃

Huggingface space for JanusFlow-1.3B

liked a dataset 3 months ago

Koala-36M/Koala-36M-v1

Viewer • Updated Oct 12, 2024 • 36M • 574 • 36

liked a model 3 months ago

black-forest-labs/FLUX.1-Fill-dev

Updated Nov 25, 2024 • 174k • 617

liked a dataset 3 months ago

BoyuanJiang/CVDD

Viewer • Updated Dec 20, 2024 • 1.03k • 73 • 18

liked 3 Spaces 3 months ago

Building

685

685

FLUX 3D StyleGEN

🏆

FLUX 3D StyleGEN

Running on L4

402

402

Stable Point-Aware 3D

⚡

Create 3D models from images

Running on Zero

162

162

Gaze Demo

👀

Gaze detection using Moondream