John Ho PRO
AI & ML interests
Recent Activity
Organizations
-
Build error51
Quant
💻51Display interactive data visualizations and apps
-
RunningFeatured44
Porting nanochat to Transformers: an AI modeling history lesson
📝44Learn about ML and Transformers through nanochat
-
Running on CPU UpgradeFeatured2.82k
The Smol Training Playbook
📚2.82kThe secrets to building world-class LLMs
-
Running on ZeroFeatured819
Florence 2
📉819Generate captions and analyze images with various tasks
-
Runtime errorFeatured515
Florence2 + SAM2
🔥515Segment and caption objects in images and videos
-
SleepingFeatured107
SAM2 Video Predictor
🔥107Segment and track objects in a video
-
Running22
SAM2 Video Predictor
🔥22Segment and track objects in videos
-
EvanZhouDev/open-genmoji
Text-to-Image • Updated • 148 • • 67 -
Running on ZeroFeatured619
ACE Step
😻619A Step Towards Music Generation Foundation Model
-
Running on ZeroFeatured600
DreamO
🐨600A Unified Framework for Image Customization
-
Running on ZeroFeatured951
Tile Upscaler
🚀951Enhance and upscale images with advanced controls
-
Configuration errorFeatured1.45k
EasyControl Ghibli
🦀1.45kNew Ghibli EasyControl model is now released!!
-
akiyamasho/AnimeBackgroundGAN-Miyazaki
Image-to-Image • Updated • 25 -
Runtime error72
Ghibli Multilingual Text-Rendering
🦀72Elevating Ghibli-style AI art beyond ChatGPT's capabilities.
-
Running on A100MCP44
EasyControl Ghibli
🦀44New Ghibli EasyControl model is now released!!
-
Running14
AI Video Editor
🏞14Create videos with FFMPEG + Qwen2.5-Coder
-
Searchium-ai/clip4clip-webvid150k
Text-to-Video • 0.2B • Updated • 2.6k • 40 -
RunningFeatured428
FastVLM WebGPU
🍎428Real-time video captioning powered by FastVLM
-
Runtime errorFeatured36
AudioRag Demo
🎵36Search audio for relevant chunks
-
Running on ZeroFeatured456
Parakeet-TDT-0.6b-V2
456Transcribe audio to text with timestamps
-
Running on Zero51
Fast Whisper Turbo
⚡51Ultra-fast Whisper Turbo inference ⚡
-
openai/whisper-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 2.65M • • 2.77k -
Running on ZeroFeatured342
Realtime Whisper Turbo
🤯342Realtime implementation of Whisper large turbo
-
Running on T4114
RF-DETR
🔥114SOTA real-time object detection model
-
Running on CPU Upgrade50
YOLO ARENA
🏟50compare performance of top object detectors
-
Running22
SAM2 Video Predictor
🔥22Segment and track objects in videos
-
Running on ZeroFeatured111
VLM Object Understanding
🦀111Explore object detection, visual grounding, keypoint Detecti
-
Running on ZeroFeatured108
Qwen2 VL Localization
📉108Detect objects in images using text prompts
-
RunningFeatured160
Seed1.5 VL
🚀160Seed1.5-VL API Demo
-
Runtime error2
Vision Language SmolVLM2
🌍2Video + text to text with SmolVLM2
-
Running on ZeroFeatured141
Gemma 3n E4B It
⚡141Generate text responses to images, videos, and audio
-
Runtime error9
Cantonese TTS Text To Speech
👁9Generate Cantonese speech from text
-
Running3
Cantonese TTS Playground
🔥3Generate speech from Cantonese text using selected or custom voice
-
Running on ZeroFeatured1.74k
Dia 1.6B
👯1.74kGenerate realistic dialogue from a script, using Dia!
-
Runtime errorFeatured81
Daily Paper Podcast
🎙81Generates a podcast about today's top trending paper.
-
Build error51
Quant
💻51Display interactive data visualizations and apps
-
RunningFeatured44
Porting nanochat to Transformers: an AI modeling history lesson
📝44Learn about ML and Transformers through nanochat
-
Running on CPU UpgradeFeatured2.82k
The Smol Training Playbook
📚2.82kThe secrets to building world-class LLMs
-
Running14
AI Video Editor
🏞14Create videos with FFMPEG + Qwen2.5-Coder
-
Searchium-ai/clip4clip-webvid150k
Text-to-Video • 0.2B • Updated • 2.6k • 40 -
RunningFeatured428
FastVLM WebGPU
🍎428Real-time video captioning powered by FastVLM
-
Runtime errorFeatured36
AudioRag Demo
🎵36Search audio for relevant chunks
-
Running on ZeroFeatured456
Parakeet-TDT-0.6b-V2
456Transcribe audio to text with timestamps
-
Running on Zero51
Fast Whisper Turbo
⚡51Ultra-fast Whisper Turbo inference ⚡
-
openai/whisper-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 2.65M • • 2.77k -
Running on ZeroFeatured342
Realtime Whisper Turbo
🤯342Realtime implementation of Whisper large turbo
-
Running on ZeroFeatured819
Florence 2
📉819Generate captions and analyze images with various tasks
-
Runtime errorFeatured515
Florence2 + SAM2
🔥515Segment and caption objects in images and videos
-
SleepingFeatured107
SAM2 Video Predictor
🔥107Segment and track objects in a video
-
Running22
SAM2 Video Predictor
🔥22Segment and track objects in videos
-
Running on T4114
RF-DETR
🔥114SOTA real-time object detection model
-
Running on CPU Upgrade50
YOLO ARENA
🏟50compare performance of top object detectors
-
Running22
SAM2 Video Predictor
🔥22Segment and track objects in videos
-
Running on ZeroFeatured111
VLM Object Understanding
🦀111Explore object detection, visual grounding, keypoint Detecti
-
Running on ZeroFeatured108
Qwen2 VL Localization
📉108Detect objects in images using text prompts
-
RunningFeatured160
Seed1.5 VL
🚀160Seed1.5-VL API Demo
-
Runtime error2
Vision Language SmolVLM2
🌍2Video + text to text with SmolVLM2
-
Running on ZeroFeatured141
Gemma 3n E4B It
⚡141Generate text responses to images, videos, and audio
-
EvanZhouDev/open-genmoji
Text-to-Image • Updated • 148 • • 67 -
Running on ZeroFeatured619
ACE Step
😻619A Step Towards Music Generation Foundation Model
-
Running on ZeroFeatured600
DreamO
🐨600A Unified Framework for Image Customization
-
Running on ZeroFeatured951
Tile Upscaler
🚀951Enhance and upscale images with advanced controls
-
Runtime error9
Cantonese TTS Text To Speech
👁9Generate Cantonese speech from text
-
Running3
Cantonese TTS Playground
🔥3Generate speech from Cantonese text using selected or custom voice
-
Running on ZeroFeatured1.74k
Dia 1.6B
👯1.74kGenerate realistic dialogue from a script, using Dia!
-
Runtime errorFeatured81
Daily Paper Podcast
🎙81Generates a podcast about today's top trending paper.
-
Configuration errorFeatured1.45k
EasyControl Ghibli
🦀1.45kNew Ghibli EasyControl model is now released!!
-
akiyamasho/AnimeBackgroundGAN-Miyazaki
Image-to-Image • Updated • 25 -
Runtime error72
Ghibli Multilingual Text-Rendering
🦀72Elevating Ghibli-style AI art beyond ChatGPT's capabilities.
-
Running on A100MCP44
EasyControl Ghibli
🦀44New Ghibli EasyControl model is now released!!