John Ho PRO
AI & ML interests
Recent Activity
Organizations
- Running17
Quant
π»17Create interactive web apps with Python in minutes
- Configuration errorFeatured89
LFM2 WebGPU β In-browser tool calling
π89In-browser tool calling, powered by Transformers.js
- Running3.28k
AnyCoder
π3.28kGenerate code snippets and app templates with AI
- RunningFeatured56
Privacy Filter WebGPU
π΅56PII detection and text masking in your browser
- Running on ZeroAgentsFeatured63
LightGlue
β63LightGlue demo
- Running on ZeroMCPFeatured33
Qwen3 VL HF Demo
π₯33Object Detection, Visual Grounding, Keypoint Detection
-
prithivMLmods/MetaCLIP-2-Age-Range-Estimator
Image Classification β’ 21.7M β’ Updated β’ 579 β’ 7 - RunningFeatured756
Remove Background Web
πΌ756In-browser background removal
- RunningAgents18
AI Video Editor
π18Create videos with FFMPEG + Qwen2.5-Coder
-
Searchium-ai/clip4clip-webvid150k
Text-to-Video β’ 0.2B β’ Updated β’ 932 β’ 45 - Configuration errorFeatured446
FastVLM WebGPU
π446Real-time video captioning powered by FastVLM
- SleepingAgentsFeatured36
AudioRag Demo
π΅36Search audio for relevant chunks
- Running on ZeroAgentsFeatured472
Parakeet-TDT-0.6b-V2
Β472Transcribe audio files with timestamps and downloadable subtitles
- Running on ZeroAgents52
Fast Whisper Turbo
β‘52Ultra-fast Whisper Turbo inference β‘
-
openai/whisper-large-v3-turbo
Automatic Speech Recognition β’ 0.8B β’ Updated β’ 8.05M β’ β’ 3.04k - Runtime errorAgentsFeatured344
Realtime Whisper Turbo
π€―344Realtime implementation of Whisper large turbo
- Running on T4Agents143
RF-DETR
π₯143SOTA real-time object detection model
- Running on CPU UpgradeAgents50
YOLO ARENA
π50compare performance of top object detectors
- RunningAgents23
SAM2 Video Predictor
π₯23Segment and track objects in videos
- Running on ZeroAgentsFeatured115
VLM Object Understanding
π¦115Explore object detection, visual grounding, keypoint Detecti
- Runtime errorAgentsFeatured110
Qwen2 VL Localization
π110Detect objects in images using text prompts
- Build errorAgentsFeatured161
Seed1.5 VL
π161Seed1.5-VL API Demo
- Runtime errorAgents2
Vision Language SmolVLM2
π2Video + text to text with SmolVLM2
- Running on ZeroAgentsFeatured143
Gemma 3n E4B It
β‘143Chat with AI using text, images, audio, or video
- Runtime errorAgents9
Cantonese TTS Text To Speech
π9Generate Cantonese speech from text
- Runtime errorAgents4
Cantonese TTS Playground
π₯4Generate speech from Cantonese text using selected or custom voice
- Running on ZeroAgentsFeatured1.78k
Dia 1.6B
π―1.78kGenerate realistic dialogue from a script, using Dia!
- Runtime errorAgentsFeatured81
Daily Paper Podcast
π81Generates a podcast about today's top trending paper.
- RunningAgentsFeatured246
PaddleOCR-VL Online Demo
π246Extract text, tables, formulas, and charts from images
- Running on ZeroAgentsFeatured449
DeepSeek OCR Demo
π449An interactive demo for the DeepSeek-OCR model.
- Running on ZeroAgentsFeatured115
LightOnOCR 2 1B Demo
π¨115Extract text and layout from images or PDF documents
- Running on ZeroMCPFeatured142
Multimodal OCR2
π»142FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
- Build error51
Quant
π»51Display interactive data visualizations and apps
- RunningFeatured49
Porting nanochat to Transformers: an AI modeling history lesson
π49Learn about ML and Transformers through nanochat
- Running on CPU UpgradeFeatured3.19k
The Smol Training Playbook
π3.19kThe secrets to building world-class LLMs
- Running on ZeroAgents27
EfficientTAM
π»27Efficient Track Anything
- PausedAgents39
EdgeTAM
π39On-Device Track Anything Model
- Running on ZeroAgentsFeatured61
EdgeTAM
π61On-Device Track Anything Model
- Running on ZeroAgents12
SAM3
π₯12All the powerful features of the SAM 3 model!
- Running on ZeroAgentsFeatured844
Florence 2
π844Generate captions, detections, and segmentations for any image
- Running on ZeroAgentsFeatured517
Florence2 + SAM2
π₯517Segment objects in images or videos using text prompts
- SleepingAgentsFeatured119
SAM2 Video Predictor
π₯119Generate object masks and masked video from your MP4
- RunningAgents23
SAM2 Video Predictor
π₯23Segment and track objects in videos
-
EvanZhouDev/open-genmoji
Text-to-Image β’ Updated β’ 72 β’ β’ 68 - Running on ZeroAgentsFeatured661
ACE Step
π»661A Step Towards Music Generation Foundation Model
- Running on ZeroAgentsFeatured600
DreamO
π¨600A Unified Framework for Image Customization
- Running on ZeroAgentsFeatured994
Tile Upscaler
π994Upscale and enhance images with tileβaware AI
- Runtime errorAgentsFeatured1.45k
EasyControl Ghibli
π¦1.45kNew Ghibli EasyControl model is now released!!
-
akiyamasho/AnimeBackgroundGAN-Miyazaki
Image-to-Image β’ Updated β’ 25 - Build errorAgents249
Ghibli Multilingual Text-Rendering
π¦249Elevating Ghibli-style AI art beyond ChatGPT's capabilities.
- Build errorMCP46
EasyControl Ghibli
π¦46New Ghibli EasyControl model is now released!!
- RunningAgentsFeatured246
PaddleOCR-VL Online Demo
π246Extract text, tables, formulas, and charts from images
- Running on ZeroAgentsFeatured449
DeepSeek OCR Demo
π449An interactive demo for the DeepSeek-OCR model.
- Running on ZeroAgentsFeatured115
LightOnOCR 2 1B Demo
π¨115Extract text and layout from images or PDF documents
- Running on ZeroMCPFeatured142
Multimodal OCR2
π»142FireRed / Nanonets / Monkey / Thyme / Typhoon / SmolDocling
- Running17
Quant
π»17Create interactive web apps with Python in minutes
- Configuration errorFeatured89
LFM2 WebGPU β In-browser tool calling
π89In-browser tool calling, powered by Transformers.js
- Running3.28k
AnyCoder
π3.28kGenerate code snippets and app templates with AI
- RunningFeatured56
Privacy Filter WebGPU
π΅56PII detection and text masking in your browser
- Running on ZeroAgentsFeatured63
LightGlue
β63LightGlue demo
- Running on ZeroMCPFeatured33
Qwen3 VL HF Demo
π₯33Object Detection, Visual Grounding, Keypoint Detection
-
prithivMLmods/MetaCLIP-2-Age-Range-Estimator
Image Classification β’ 21.7M β’ Updated β’ 579 β’ 7 - RunningFeatured756
Remove Background Web
πΌ756In-browser background removal
- Build error51
Quant
π»51Display interactive data visualizations and apps
- RunningFeatured49
Porting nanochat to Transformers: an AI modeling history lesson
π49Learn about ML and Transformers through nanochat
- Running on CPU UpgradeFeatured3.19k
The Smol Training Playbook
π3.19kThe secrets to building world-class LLMs
- RunningAgents18
AI Video Editor
π18Create videos with FFMPEG + Qwen2.5-Coder
-
Searchium-ai/clip4clip-webvid150k
Text-to-Video β’ 0.2B β’ Updated β’ 932 β’ 45 - Configuration errorFeatured446
FastVLM WebGPU
π446Real-time video captioning powered by FastVLM
- SleepingAgentsFeatured36
AudioRag Demo
π΅36Search audio for relevant chunks
- Running on ZeroAgents27
EfficientTAM
π»27Efficient Track Anything
- PausedAgents39
EdgeTAM
π39On-Device Track Anything Model
- Running on ZeroAgentsFeatured61
EdgeTAM
π61On-Device Track Anything Model
- Running on ZeroAgents12
SAM3
π₯12All the powerful features of the SAM 3 model!
- Running on ZeroAgentsFeatured472
Parakeet-TDT-0.6b-V2
Β472Transcribe audio files with timestamps and downloadable subtitles
- Running on ZeroAgents52
Fast Whisper Turbo
β‘52Ultra-fast Whisper Turbo inference β‘
-
openai/whisper-large-v3-turbo
Automatic Speech Recognition β’ 0.8B β’ Updated β’ 8.05M β’ β’ 3.04k - Runtime errorAgentsFeatured344
Realtime Whisper Turbo
π€―344Realtime implementation of Whisper large turbo
- Running on ZeroAgentsFeatured844
Florence 2
π844Generate captions, detections, and segmentations for any image
- Running on ZeroAgentsFeatured517
Florence2 + SAM2
π₯517Segment objects in images or videos using text prompts
- SleepingAgentsFeatured119
SAM2 Video Predictor
π₯119Generate object masks and masked video from your MP4
- RunningAgents23
SAM2 Video Predictor
π₯23Segment and track objects in videos
- Running on T4Agents143
RF-DETR
π₯143SOTA real-time object detection model
- Running on CPU UpgradeAgents50
YOLO ARENA
π50compare performance of top object detectors
- RunningAgents23
SAM2 Video Predictor
π₯23Segment and track objects in videos
- Running on ZeroAgentsFeatured115
VLM Object Understanding
π¦115Explore object detection, visual grounding, keypoint Detecti
- Runtime errorAgentsFeatured110
Qwen2 VL Localization
π110Detect objects in images using text prompts
- Build errorAgentsFeatured161
Seed1.5 VL
π161Seed1.5-VL API Demo
- Runtime errorAgents2
Vision Language SmolVLM2
π2Video + text to text with SmolVLM2
- Running on ZeroAgentsFeatured143
Gemma 3n E4B It
β‘143Chat with AI using text, images, audio, or video
-
EvanZhouDev/open-genmoji
Text-to-Image β’ Updated β’ 72 β’ β’ 68 - Running on ZeroAgentsFeatured661
ACE Step
π»661A Step Towards Music Generation Foundation Model
- Running on ZeroAgentsFeatured600
DreamO
π¨600A Unified Framework for Image Customization
- Running on ZeroAgentsFeatured994
Tile Upscaler
π994Upscale and enhance images with tileβaware AI
- Runtime errorAgents9
Cantonese TTS Text To Speech
π9Generate Cantonese speech from text
- Runtime errorAgents4
Cantonese TTS Playground
π₯4Generate speech from Cantonese text using selected or custom voice
- Running on ZeroAgentsFeatured1.78k
Dia 1.6B
π―1.78kGenerate realistic dialogue from a script, using Dia!
- Runtime errorAgentsFeatured81
Daily Paper Podcast
π81Generates a podcast about today's top trending paper.
- Runtime errorAgentsFeatured1.45k
EasyControl Ghibli
π¦1.45kNew Ghibli EasyControl model is now released!!
-
akiyamasho/AnimeBackgroundGAN-Miyazaki
Image-to-Image β’ Updated β’ 25 - Build errorAgents249
Ghibli Multilingual Text-Rendering
π¦249Elevating Ghibli-style AI art beyond ChatGPT's capabilities.
- Build errorMCP46
EasyControl Ghibli
π¦46New Ghibli EasyControl model is now released!!