Valeriy Selitskiy PRO

WaveCut's activity

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

upvoted a paper about 10 hours ago

The Free Transformer

Paper • 2510.17558 • Published Oct 20, 2025 • 6

liked a model about 12 hours ago

tencent/HunyuanImage-3.0-Instruct

Image-to-Image • Updated 22 days ago • 1.55k • • 363

liked a model about 13 hours ago

dx8152/Flux2-Klein-9B-Enhanced-Details

Image-to-Image • Updated about 19 hours ago • 20

upvoted a collection about 18 hours ago

💧 LFM2

Collection

LFM2 is a new generation of hybrid models, designed for on-device deployment. • 31 items • Updated about 20 hours ago • 141

liked a model about 18 hours ago

LiquidAI/LFM2-24B-A2B

Text Generation • 24B • Updated about 12 hours ago • 1.57k • 115

liked a model about 19 hours ago

xgen-universe/Capybara

Any-to-Any • Updated 2 days ago • 182

upvoted a collection about 20 hours ago

ParoQuant

Collection

Pairwise Rotation Quantization for Efficient Reasoning LLM Inference • 18 items • Updated 1 day ago • 3

liked a model 7 days ago

deepgenteam/DeepGen-1.0

Text-to-Image • Updated 4 days ago • 101 • 154

liked 4 models 8 days ago

Cordux/flux2-klein-4B-uncensored-text-encoder

4B • Updated 29 days ago • 2.68k • 45

fal/flux-2-klein-4B-outpaint-lora

Image-to-Image • Updated Jan 21 • • 58

CodeGoat24/FLUX.2-klein-base-9B-UnifiedReward-Flex-lora

Text-to-Image • Updated 17 days ago • 436 • 17

CohereLabs/tiny-aya-water

Text Generation • 3B • Updated 1 day ago • 602 • 23

upvoted a collection 8 days ago

Tiny Aya

Collection

Bridging Scale and Multilingual Depth • 10 items • Updated 8 days ago • 60

liked a Space 8 days ago

Running on Zero

MCP

Featured

61

BitDance-14B-64x

🚀

61

Open-source autoregressive model with binary visual tokens.

liked a model 8 days ago

shallowdream204/BitDance-14B-64x

Text-to-Image • 15B • Updated 7 days ago • 341 • 58

upvoted a collection 8 days ago

BitDance

Collection

BitDance: Open-source autoregressive model with binary visual tokens. A research project for building powerful multimodal autoregressive model. • 11 items • Updated 3 days ago • 9

liked a model 8 days ago

Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice

Text-to-Speech • Updated 27 days ago • 1.03M • 1.19k

liked 2 models 9 days ago

nvidia/music-flamingo-think-2601-hf

Audio-Text-to-Text • 8B • Updated 1 day ago • 392 • 19

anemll/anemll-Nanbeige-Nanbeige4.1-3B-ctx4096_0.3.5

Updated 10 days ago • 39 • 1

upvoted a collection 9 days ago

Nanbeige4.1-3B

Collection

4 items • Updated 9 days ago • 2