1 215

Boon

beowcow

AI & ML interests

nodejs, python, gan, tts

Recent Activity

liked a Space 9 days ago

techfreakworm/LTX2.3-Studio

liked a Space 14 days ago

openbmb/VoxCPM-Demo

updated a model 17 days ago

beowcow/chsges

View all activity

Organizations

None yet

liked a Space 9 days ago

LTX 2.3 Studio

🎬

133

Generate videos from text, audio, images, or style references

liked a Space 14 days ago

VoxCPM Demo

🎙

480

VoxCPM2 Nano-vLLM Demo

liked 2 Spaces about 1 month ago

HY World 2.0 Demo

🤗

A Multi-Modal World Model for Reconstruction

OmniVoice

🌍

896

High-quality voice cloning TTS for 600+ languages

liked 4 Spaces 2 months ago

LTX 2.3 First-Last Frame

🎥

128

Generate videos from text, images, and audio

TADA — Text-Acoustic Dual Alignment for Speech

🗯

Speech generation from text and acoustic reference

FireRed Image Edit 1.0 Fast

🌖

1.32k

FireRed-Image-Edit × Qwen-Image-Edit-Rapid (Transformers)

LTX 2.3 Distilled

📚

344

Generate cinematic videos with audio from text prompts

liked 2 Spaces 4 months ago

Qwen3-TTS Demo

🎙

1.93k

Generate speech from text via voice design, cloning, or presets

NovaSR

🐢

An incredibly fast and tiny audio upsampler

liked 2 Spaces 5 months ago

Qwen Image to LoRA

😭

347

Generate LoRA from a single image

AnyTalker

🎬

Let your character interact naturally

liked 2 Spaces 6 months ago

Echo-TTS Preview

🐢

118

Fast, multi-speaker TTS (44.1kHz) with voice cloning

HunyuanVideo 1.5 I2V 480p

🌍

105

Generate videos from images and prompts

liked a model 6 months ago

tencent/HunyuanVideo-1.5

Text-to-Video • Updated Dec 25, 2025 • 2.04k • • 988

liked 2 Spaces 6 months ago

Step-Audio-EditX

🚀

102

Try out Step-Audio-EditX

Qwen3 VL Demo

😻

433

Chat with an AI that understands text, images, and videos

liked 3 Spaces 8 months ago

Ovi [local]

🎥

269

Generate Hollywood Style Actors on your Local Machine

Whisper Large V3

🤫

842

Transcribe or translate audio and YouTube videos to text

VoxCPM 0.5B

🐢

Generate expressive speech from text with optional voice cloning