SmolVLM 256M Instruct WebGPU
🐨
72
Generate captions for your images instantly
Image
-
-
deepseek-ai/Janus-Pro-7B
Any-to-Any • Updated • 12.5k • 3.62k -
Qwen/Qwen2.5-VL-72B-Instruct
Image-Text-to-Text • 73B • Updated • 497k • • 630 -
BEN2
🚀228Remove background from images and videos
-
Paligemma2 Mix
🌖97Generate text answers or segment objects from images
-
SmolVLM
📊81Generate answers by combining text and images
-
Compare Siglip1 Siglip2
🚀54Compare SigLIP1 and SigLIP2 on zero shot classification
-
CohereLabs/aya-vision-32b
Image-Text-to-Text • 33B • Updated • 411 • • 227 -
Yoloe
🚀68Detect and segment objects in images using text, visual, or prompt-free prompts
-
Distill Any Depth
💻181Generate depth map from your photo
-
Thera Arbitrary-Scale Super-Resolution
🔥283Upscale photos to any size with neural super‑resolution
-
starvector/starvector-8b-im2svg
8B • Updated • 33.4k • 558 -
ByteDance/InfiniteYou
Text-to-Image • Updated • 898 • 643 -
jameslahm/yoloe
Object Detection • Updated • 4.46k • 45 -
KV-Edit
🎨40Precise Background Preservation in Editing
-
Step1X Edit
💻362Edit an image based on the given instruction.
-
Chain-of-Zoom
🚀321Extreme Super-Resolution via Scale Autoregression
-
FLUX.1 [Schnell]
🏎50Generate images from text descriptions
-
GLM-4.1V-9B-Thinking-Demo
🐢64THUDM/GLM-4.1V-9B-Thinking Demo
-
Qwen/Qwen-Image-Edit
Image-to-Image • Updated • 69.9k • • 2.43k -
USO FLUX
⚡301Generate custom images with style and subject references
-
VLM Object Understanding
🦀119Explore object detection, visual grounding, keypoint Detecti