Alex

asigalov61's activity

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

New activity in SyMuPe/PianoCoRe about 13 hours ago

Thank you!

#2 opened about 13 hours ago by

asigalov61

liked a model about 13 hours ago

SyMuPe/PianoFlow-base

24.5M • Updated May 8 • 29 • 1

liked 2 models 3 days ago

ai-sage/GigaChat3.1-10B-A1.8B-bf16

Text Generation • 11B • Updated Mar 25 • 5.83k • 16

ai-sage/GigaChat-20B-A3B-instruct-bf16

Text Generation • 21B • Updated Jun 25, 2025 • 32 • 16

liked 2 Spaces 3 days ago

Runtime error

Agents

263

Singing Voice Conversion

🎼

263

Transform your voice into a singer's

Runtime error

Agents

2

HearMe — Singing Voice Improver

🎤

2

Improve your singing with pitch‑corrected audio

reacted to projectlosangeles's post with 🤗 21 days ago

view post

Post

6527

🔥If you love multi-modal art🎨, please check out "A Million Little Fibers" project!!!🔥

https://github.com/asigalov61/A-Million-Little-Fibers-2026

https://soundcloud.com/aleksandr-sigalov-61/sets/a-million-little-fibers

This brand new 2026 edition covers three SOTA models:

zai-org/GLM-5.2
k2-fsa/OmniVoice
HeartMuLa/HeartMuLa-oss-3B-happy-new-year

The project aims to showcase what kind of multi-modal art is now possible to create with these amazing OSS resources!

If you enjoyed the project, please ⭐or 🔱 GitHub repo and❤️on SoundCloud and Hugging Face. It really helps!

Most sincerely,

Alex

Project Los Angeles
Tegridy Code 2026

P.S. Don't forget to bring a towel! 😂

@multimodalart
@victor
@John6666

See translation

• 

• 
• 
• 
• 3 replies

·

🔥

6

6

❤️

3

3

👀

3

3

🤗

2

2

+

Reply

liked 2 Spaces 21 days ago

Running on Zero

Agents

Featured

402

LTX 2.3 Distilled

📚

402

Generate cinematic videos with audio from text prompts

Running on Zero

Agents

23

LTX 2.3 HDR

🎞

23

Generate HDR video from your source clip

liked a model 21 days ago

Lightricks/LTX-2.3

Image-to-Video • Updated 10 days ago • 2.13M • 1.61k

reacted to projectlosangeles's post with 👀❤️🔥 21 days ago

view post

Post

6527

🔥If you love multi-modal art🎨, please check out "A Million Little Fibers" project!!!🔥

https://github.com/asigalov61/A-Million-Little-Fibers-2026

https://soundcloud.com/aleksandr-sigalov-61/sets/a-million-little-fibers

This brand new 2026 edition covers three SOTA models:

zai-org/GLM-5.2
k2-fsa/OmniVoice
HeartMuLa/HeartMuLa-oss-3B-happy-new-year

The project aims to showcase what kind of multi-modal art is now possible to create with these amazing OSS resources!

If you enjoyed the project, please ⭐or 🔱 GitHub repo and❤️on SoundCloud and Hugging Face. It really helps!

Most sincerely,

Alex

Project Los Angeles
Tegridy Code 2026

P.S. Don't forget to bring a towel! 😂

@multimodalart
@victor
@John6666

See translation

• 

• 
• 
• 
• 3 replies

·

🔥

6

6

❤️

3

3

👀

3

3

🤗

2

2

+

Reply

liked a model 22 days ago

k2-fsa/OmniVoice

Text-to-Speech • 0.6B • Updated 16 days ago • 880k • 1.18k

liked 2 Spaces 22 days ago

Running on Zero

Agents

5

OmniVoice Singing

🎤

5

Singing & emotional TTS, voice cloning for 600+ languages

Running on Zero

Agents

Featured

2.06k

Qwen3-TTS Demo

🎙

2.06k

Generate speech from text using voice design, cloning or presets

liked a model 23 days ago

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

Text-to-Speech • 2B • Updated Jan 29 • 714k • 374

liked a Space 23 days ago

Running on Zero

Agents

4

HeartMuLa

❤

4

The best open-source music generation model of 2026

liked 2 datasets 24 days ago

kkwsts/pianojudge-techniques-midi

Viewer • Updated Apr 18 • 222 • 45 • 1

k-nar/piano_chunks

Viewer • Updated Apr 22 • 115k • 94 • 1