Julien BLANCHON PRO

blanchon's activity

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

liked 2 models about 4 hours ago

stepfun-ai/NextStep-1.1-Pretrain

Text-to-Image • 15B • Updated about 18 hours ago • 5

stepfun-ai/NextStep-1.1

Text-to-Image • 15B • Updated 1 day ago • 15

upvoted a paper about 16 hours ago

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

Paper • 2511.22677 • Published 27 days ago • 28

liked a Space about 17 hours ago

Running on Zero

4

NextStep 1 Large

🖼

4

An example for using NextStep-1-Large

liked 3 models about 17 hours ago

stepfun-ai/NextStep-1-Large-Edit

Image-to-Image • 15B • Updated Aug 19 • 116 • 50

stepfun-ai/NextStep-1-Large-Pretrain

Text-to-Image • 15B • Updated Oct 10 • 1.07k • 18

stepfun-ai/NextStep-1-Large

Text-to-Image • 15B • Updated Aug 19 • 3.14k • 97

upvoted a collection about 17 hours ago

NextStep-1

Collection

9 items • Updated about 19 hours ago • 31

liked a Space about 18 hours ago

Running on Zero

MCP

59

Qwen Image Edit 2511 Fast

🏆

59

Fast 4 step inference of Qwen Image Edit 2511

liked a model about 19 hours ago

lightx2v/Qwen-Image-Edit-2511-Lightning

Updated about 15 hours ago • 14.4k • 102

liked a Space about 19 hours ago

Running on Zero

5

Qwen-Image-Edit-2511-Lightning

📚

5

Edit images using AI with a simple prompt

liked 2 models 1 day ago

meituan-longcat/LongCat-Image-Dev

Text-to-Image • Updated 9 days ago • 206 • 40

kyutai/CASA-Helium1-VL-2B

Image-Text-to-Text • 3B • Updated 1 day ago • 72 • 4

liked a Space 1 day ago

Running

1

CASA Gallery

🏠

1

Video Gallery for CASA: Cross-Attention via Self-Attention

upvoted a collection 1 day ago

CASA

Collection

CASA: Cross-Attention as Self-Attention for Efficient Vision-Language Fusion on long context streaming inputs • 6 items • Updated 1 day ago • 4

liked 3 models 1 day ago

Qwen/Qwen-Image-Edit-2511

Image-to-Image • Updated 1 day ago • 1.15k • • 299

FunAudioLLM/Fun-Audio-Chat-8B

Any-to-Any • 9B • Updated about 12 hours ago • 71 • 34

nunchaku-tech/nunchaku-z-image-turbo

Text-to-Image • Updated 4 days ago • 6.2k • 59

upvoted a paper 2 days ago

3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework

Paper • 2512.17459 • Published 5 days ago • 7

liked a Space 2 days ago

Running on Zero

Featured

41

SHARP - 3D Gaussian Scene Prediction

🔪

41

Sharp Monocular View Synthesis in Less Than a Second