Nemotron ColEmbed V2
Collection
State-of-the-Art Late Interaction Vision-Language Embedding Models • 3 items • Updated • 15
Jan 19 Releases
-
-
Qwen/Qwen3-TTS-12Hz-1.7B-Base
2B • Updated • 2.55M • 468 -
fal/flux-2-klein-4B-outpaint-lora
Image-to-Image • Updated • • 88 -
Qwen/Qwen3-TTS-Tokenizer-12Hz
Audio-to-Audio • 0.2B • Updated • 149k • 75 -
bevaya/GutenOCR-7B
Image-Text-to-Text • 8B • Updated • 135 • 25 -
nvidia/Qwen3-8B-DMS-8x
8B • Updated • 1.95k • 37 -
fal/flux-2-klein-4b-spritesheet-lora
Image-to-Image • Updated • • 87 -
Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice
Text-to-Speech • 0.9B • Updated • 1.6M • 173 -
LiquidAI/LFM2.5-1.2B-Thinking
Text Generation • 1B • Updated • 38k • 390 -
Qwen/Qwen3-TTS-12Hz-0.6B-Base
Text-to-Speech • 0.9B • Updated • 445k • 273 -
meituan-longcat/LongCat-Flash-Thinking-ZigZag
Text Generation • 562B • Updated • 48 • 32 -
sweepai/sweep-next-edit-1.5B
1B • Updated • 1.25k • 326 -
mlx-community/GLM-4.7-Flash-8bit
Text Generation • 30B • Updated • 3.54k • 24 -
fal/flux-2-klein-4B-zoom-lora
Image-to-Image • Updated • • 48 -
zai-org/GLM-4.7-Flash
Text Generation • 31B • Updated • 2.07M • • 1.8k -
Linum-AI/linum-v2-720p
Text-to-Video • Updated • 95 -
cerebras/GLM-4.7-Flash-REAP-23B-A3B
Text Generation • 23B • Updated • 982 • 81 -
openbmb/AgentCPM-Report
Text Generation • 8B • Updated • 1.05k • 305 -
fal/flux-2-klein-4B-background-remove-lora
Image-to-Image • Updated • • 26 -
Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice
Text-to-Speech • 2B • Updated • 2.31M • 1.86k -
Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign
Text-to-Speech • 2B • Updated • 574k • 383 -
HeartMuLa/HeartMuLa-RL-oss-3B-20260123
4B • Updated • 248 • 26 -
Overworld/Waypoint-1-Small
3B • Updated • 30 • 122 -
cyrildiagne/flux2-klein9b-lora-mlsharp-3d-repair
Updated • 122 -
microsoft/VibeVoice-ASR
Automatic Speech Recognition • 9B • Updated • 695k • 1.25k -
YatharthS/LuxTTS
Text-to-Speech • Updated • 7.97k • 201 -
Emperorizzis/ASTRA-SFT-1k
Viewer • Updated • 1k • 140 • 16 -
opendatalab/ChartVerse-SFT-1.8M
Viewer • Updated • 1.88M • 2.53k • 138 -
otoearth/otoSpeech-full-duplex-processed-141h
Preview • Updated • 209 • 29 -
google/WaxalNLP
Preview • Updated • 73.2k • 264 -
LuxTTS
🚀110Space for LuxTTS: a 150x realtime voice cloning TTS model
-
Fibo Edit
🚀20Edit images with AI‑powered FIBO model
-
LightOnOCR 2 1B Demo
🐨123Extract text and layout from images or PDF documents
-
Qwen3-TTS Demo
🎙2.11kGenerate speech from text using voice design, cloning or presets