Comfy-Org/Ideogram-4
Updated • 249k • 267
Weekly Releases (Jun 05, 2026)
-
-
jdopensource/JoyAI-Echo
Image-to-Video • 19B • Updated • 401 • 178 -
litert-community/gemma-4-12B-it-litert-lm
Updated • 11.8k • 64 -
google/gemma-4-12B-it-qat-q4_0-unquantized
Any-to-Any • 12B • Updated • 13.5k • 85 -
dots-studio/dots.tts-soar
Text-to-Speech • 2B • Updated • 2.4k • 93 -
nex-agi/Nex-N2-mini
Text Generation • 35B • Updated • 1.2k • • 310 -
Trendyol/Trendyol-TTS
Text-to-Speech • 2B • Updated • 570 • 39 -
nomadoor/flux-2-klein-9B-schematic-lora
Image-Text-to-Image • Updated • • 86 -
google/gemma-4-31B-it-qat-w4a16-ct
Image-Text-to-Text • 34B • Updated • 283k • 80 -
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
Text Generation • 561B • Updated • 807k • • 364 -
dots-studio/dots.tts-base
Text-to-Speech • 2B • Updated • 337 • 53 -
CohereLabs/North-Mini-Code-1.0
Text Generation • 30B • Updated • 7.69k • 577 -
Hcompany/Holo-3.1-35B-A3B-NVFP4
Image-Text-to-Text • 19B • Updated • 844 • 41 -
google/gemma-4-12B-it-qat-w4a16-ct
Any-to-Any • 13B • Updated • 841k • 60 -
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4
Text Generation • 303B • Updated • 158k • • 356 -
SupraLabs/Supra-50M-Reasoning
Text Generation • 51.8M • Updated • 372 • 63 -
LiconStudio/LTX-2.3-Multiple-Subject-Reference
Updated • 7.83k • 261 -
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-Base-BF16
Text Generation • 561B • Updated • 962 • 35 -
ByteDance/Bernini-R
Image-Text-to-Video • Updated • 75 • 299 -
google/gemma-4-E2B-it-qat-mobile-transformers
Any-to-Any • 2B • Updated • 2.78k • 155 -
Abiray/Wan22_Bernini_FP8_Scaled
Image-Text-to-Video • Updated • 25 -
nex-agi/Nex-N2-Pro
Text Generation • 397B • Updated • 976 • 376 -
bosonai/higgs-tts-3-4b
Text-to-Speech • 5B • Updated • 105k • 801 -
JGOS-Model/JGOS-31B-Citizen
Image-Text-to-Text • 31B • Updated • 52 • 31 -
ideogram-ai/ideogram-4-nf4-diffusers
Text-to-Image • 5B • Updated • 1.24k • 42 -
ServiceNow-AI/eva-bench
Viewer • Updated • 213 • 107 • 25 -
nvidia/Nemotron-Personas-El-Salvador
Viewer • Updated • 148k • 564 • 58 -
nvidia/Nemotron-Pretraining-Legal-v1
Viewer • Updated • 9.62M • 980 • 25 -
julien-c/synthtraces
Traces • Updated • 2.88k • 3.15k • 32 -
microsoft/RHELM
Viewer • Updated • 1.31k • 1.09k • 16 -
nvidia/Nemotron-Personas-Vietnam
Viewer • Updated • 100k • 779 • 62 -
Miso TTS 8B
🍲428B CSM-style text-to-speech with voice cloning
-
TripoSplat
👁346Generate a 3D model from a single image
-
Dots.tts
👁58Generate speech audio from text
-
Ideogram 4
🎨256Ideogram 4 state of the art open weights
-
Cosmos3-Nano
🌌62NVIDIA Cosmos3-Nano — text/image to video + audio
-
Gemma 4 12B IT
⚡155Chat with an AI using text, images, audio, or video