SIS

njasa's activity

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

upvoted a collection 2 days ago

QLIP

Collection

QLIP is a family of image tokenizers with SOTA reconstruction quality and zero-shot image understanding. • 3 items • Updated 5 days ago • 6

liked a Space 12 days ago

Running

60

60

Background Removal Arena

⚡

Vote on background-removed images to rank models

liked a model 12 days ago

Alpha-VLLM/Lumina-Image-2.0

Text-to-Image • Updated 5 days ago • 3.74k • 211

liked a Space about 1 month ago

Running on Zero

230

230

TransPixar

😻

https://huggingface.co/papers/2501.03006

liked a model about 2 months ago

meta-llama/Meta-Llama-3-8B

Text Generation • Updated Sep 27, 2024 • 648k • 6.01k

liked 2 datasets about 2 months ago

wang-sj16/TI2V-Bench

Viewer • Updated Dec 25, 2024 • 88 • 84 • 1

chaenayo/PODS

Viewer • Updated Dec 23, 2024 • 12.4k • 46 • 3

liked 2 models about 2 months ago

hlwang06/LeviTor

Updated Dec 18, 2024 • 29 • 4

FastVideo/FastMochi-diffusers

Text-to-Video • Updated Dec 16, 2024 • 117 • 17

liked 2 models 2 months ago

SWivid/F5-TTS

Text-to-Speech • Updated Nov 8, 2024 • 1.15M • 896

Xiaomabufei/lumos

Updated Dec 11, 2024 • 8

upvoted a collection 2 months ago

[MASK] is All You Need

Collection

Code, dataset, and pretrained model • 6 items • Updated 6 days ago • 9

liked a model 2 months ago

Zlikwid/Zlikwid_CogVideoX-1.5-5B-I2V

Updated Dec 9, 2024 • 2

liked a Space 2 months ago

Running on Zero

221

221

FLUX.1 Fill Dev

🖌

Generate detailed image edits and inpainting using prompts

commented a paper 3 months ago

Diffusion Self-Distillation for Zero-Shot Customized Image Generation

Paper • 2411.18616 • Published Nov 27, 2024 • 15 •

6

upvoted a collection 3 months ago

Sana

Collection

⚡️Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer • 21 items • Updated 1 day ago • 87

liked 2 models 4 months ago

alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta

Image-to-Image • Updated Oct 12, 2024 • 17.2k • 272

ostris/OpenFLUX.1

Text-to-Image • Updated Oct 3, 2024 • 11.7k • 629

New activity in cosmicman/CosmicManHQ-1.0 7 months ago

why is this dataset licensed cc-by-4.0 if it only non-commercial usage is allowed?

#3 opened 7 months ago by

njasa

New activity in Kwai-Kolors/Kolors 7 months ago

odd that the license is in chinese but write the description in english.

1

#6 opened 7 months ago by

njasa