AI Models

Experimental interface for AI Models Service

Available Models

YOLO

Object Detection, Segmentation, Pose & Classification

/yolo/detect/yolo/segment/yolo/pose/yolo/classify

RMBG

Background Removal & Mask Generation

/rmbg/remove/rmbg/mask

Upscale

Image Super-Resolution (2x, 4x)

/upscale/image

SAM2

Segment Anything Model 2 - Interactive Segmentation

/sam2/segment/point/sam2/segment/box/sam2/segment/auto

ImageGen

Text-to-Image Generation (Z-Image-Turbo, GLM-Image)

/imagegen/generate

Image-to-Image

Edit Images with GLM-Image (Style Transfer, Background Replacement)

/imagegen/generate/img2img

Depth

Monocular Depth Estimation

/depth/estimate

Caption

Image Captioning, Tags & Visual QA

/caption/generate/caption/tags/caption/question

Vectorize

Image to SVG Vector Conversion

/vectorize/convert/vectorize/preview

Florence-2

Vision Foundation Model - Caption, OCR, Detection, Grounding

/florence/caption/florence/ocr/florence/detect/florence/ground

GFPGAN

Face Restoration & Enhancement

/gfpgan/restore/gfpgan/enhance

ControlNet

Controlled Image Generation (Canny, Depth)

/controlnet/generate

IP-Adapter

Style & Content Transfer from Reference Images

/ipadapter/generate

SVD

Image-to-Video Generation (Stable Video Diffusion)

/svd/generate

Multiple Angles

3D Camera Control - Generate Different Viewing Angles

/multiple-angles/generate/multiple-angles/generate/batch

LTX-Video

High-Quality Video Generation (Text-to-Video & Image-to-Video)

/ltx-video/t2v/ltx-video/i2v

HunyuanVideo

Tencent 8.3B Video Generation (Text-to-Video & Image-to-Video)

/hunyuan-video/t2v/hunyuan-video/i2v

Sulphur

Uncensored LTX-2.3 22B (BF16→FP8). T2V + I2V with 2x spatial upsampler.

/sulphur/t2v/sulphur/i2v