Peter Larsen

Boosh's activity

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

New activity in mrfakename/VoiceStar 10 days ago

transcription broken

👍 1

#1 opened 10 days ago by

Boosh

liked a model 3 months ago

tencent/HunyuanVideo-I2V

Image-to-Video • Updated Mar 13 • 5.14k • 313

New activity in HKUSTAudio/Llasa-3B 4 months ago

Training data information

3

#3 opened 5 months ago by

jpgallegoar

New activity in hexgrad/Kokoro-TTS 7 months ago

when it will be available for open source community

➕ 3

17

#1 opened 7 months ago by

arpitsh018

upvoted an article 7 months ago

view article

Article

Upgrading Kokoro: natural TTS for short bursts

By •

Nov 22, 2024

• 28

replied to hexgrad's post 7 months ago

view reply

This is really ecouraging for local tts potential. Do you have any idea if the latency would be suitable for realtime chat?

liked a Space 7 months ago

Running

65

65

Podcastfy.ai - An Open Source alternative to NotebookLM's podcast feature

🚀

Generate a podcast from text, URLs, PDFs, and images

New activity in jasperai/Flux.1-dev-Controlnet-Upscaler 8 months ago

Output from medium sized image is flawed?

2

#8 opened 8 months ago by

jijov17984

upvoted 2 papers over 1 year ago

MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation

Paper • 2401.04468 • Published Jan 9, 2024 • 50

AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort

Paper • 2311.11243 • Published Nov 19, 2023 • 17

liked a model about 2 years ago

openaccess-ai-collective/mpt-7b-wizardlm

Text Generation • Updated May 17, 2023 • 33 • 21

New activity in OccamRazor/mpt-7b-storywriter-4bit-128g about 2 years ago

trust_remote_code=True

1

#3 opened about 2 years ago by

PabloTerres

Oobabooga cannot determine model type

17

#2 opened about 2 years ago by

Dingus123