FaxuanCai's picture

80

FaxuanCai

LayerNorm

·

AI & ML interests

AI art

Recent Activity

reacted to AdinaY's post with 🔥 about 20 hours ago

Qwen just released two new model series: Qwen3-VL-Embedding & Qwen3-VL-Reranker 🚀 ✨ 2B / 8B - Apache2.0 ✨ 30+ languages ✨ Supported text, images, screenshots, videos, and arbitrary multimodal combinations Qwen3-VL-Embedding: Flexible vector sizes (64–2048) https://huggingface.co/collections/Qwen/qwen3-vl-embedding Qwen3-VL-Reranker: Built for recall>rerank pipelines https://huggingface.co/collections/Qwen/qwen3-vl-reranker

liked a model 1 day ago

openbmb/VoxCPM1.5

liked a model 6 days ago

microsoft/VibeVoice-1.5B

View all activity

Organizations

None yet

liked a model 1 day ago

openbmb/VoxCPM1.5

Text-to-Speech • Updated 29 days ago • 4.4k • 277

liked a model 6 days ago

microsoft/VibeVoice-1.5B

Text-to-Speech • 3B • Updated Sep 1, 2025 • 376k • 2.16k

liked a model 7 days ago

lightx2v/Qwen-Image-2512-Lightning

Text-to-Image • Updated 4 days ago • 57.2k • 151

liked 3 models 9 days ago

Kijai/WanVideo_comfy

Updated 12 days ago • 5.52M • 1.99k

lightx2v/Wan2.2-Distill-Loras

Image-to-Video • Updated 25 days ago • 1.02M • • 180

microsoft/TRELLIS.2-4B

Image-to-3D • Updated 14 days ago • 535

liked 3 models 16 days ago

FunAudioLLM/Fun-ASR-Nano-2512

Updated 19 days ago • 809 • 133

Qwen/Qwen-Image-Layered

Image-Text-to-Image • Updated 23 days ago • 22.2k • 921

nvidia/NitroGen

Updated 3 days ago • 468

liked a model 17 days ago

Qwen/Qwen-Image-Edit-2511

Image-to-Image • Updated 18 days ago • 65.9k • • 665

liked a model 18 days ago

pcunwa/BS-Roformer-Inst-FNO

Updated 23 days ago • 7

liked a model 21 days ago

lukewys/laion_clap

Updated Apr 8, 2023 • 37

liked 2 models 22 days ago

tencent/HY-WorldPlay

Image-to-Video • Updated 5 days ago • 4.32k • 430

facebook/pe-av-large

2B • Updated 18 days ago • 778 • 45

liked 2 models about 1 month ago

bdsqlsz/qinglong_DetailedEyes_Z-Image

Text-to-Image • Updated Nov 29, 2025 • 8.81k • • 28

Tongyi-MAI/Z-Image-Turbo

Text-to-Image • Updated 4 days ago • 365k • • 3.69k

liked 4 models about 2 months ago

baidu/ERNIE-4.5-VL-28B-A3B-Thinking

Image-Text-to-Text • 30B • Updated 17 days ago • 533 • 515

OpenIXCLab/SeC-4B

Mask Generation • 4B • Updated Jul 22, 2025 • 225 • 35

VeryAladeen/Sec-4B

Image Segmentation • Updated Oct 14, 2025 • 36

tencent/HunyuanVideo-1.5

Text-to-Video • Updated 17 days ago • 599k • • 670