image23d
- Paper β’ 2312.13150 β’ Published β’ 16
- 197
Qwen-VL-Plus
π·Chat with images and text using Qwen-VL-Plus
- 266
Depth Anything Web
πΌGenerate depth map from an image
- 773
BRIA RMBG 1.4
π»Remove background from images
- 257
YOLO-World + EfficientSAM
π₯ - 594
Real-Time Text-to-Image SDXL Lightning
β‘Real-Time Image Generation with SDXL Lightning
- 56
TCD
πOfficial Demo Space for Trajectory Consistency Distillation
- 815
TripoSR
π³ - 430
moondream2
πa tiny vision language model
- 749
Florence 2
πAnalyze images to generate captions, detect objects, or perform OCR
- 29
Phi 3.5 Vision
πAsk questions about images
yifeihu/TB-OCR-preview-0.1
Image-Text-to-Text β’ Updated β’ 167 β’ 129- 252
Qwen2-VL-7B
π₯Generate text by combining an image and a question
- 1.91k
Diffusers Image Outpaint
πEasily expand image boundaries
- 1.28k
Expression Editor
π¨Quickly edit the expression of a face
- 1.96k
FacePoke
πImport a portrait, click to move the head!
- 150
Chat With Janus 1.3B
πA unified multimodal understanding and generation model.
- 1.72k
MagicQuill
πͺΆEdit and enhance images with custom color and edge modifications
- 848
LTX-Video-Playground
πGenerate videos from text or images
- 41
RollingDepth
πΉVideo Depth without Video Models
- 522
Flux Fill Outpainting
πExtend images using prompts and alignment options
- 4.55k
TRELLIS
π’Scalable and Versatile 3D Generation from images
- 47
Paligemma2 Vqav2
π¨PaliGemma2 LoRA finetuned on VQAv2
- 685
FLUX 3D StyleGEN
πFLUX 3D StyleGEN
- 382
InvSR
πImage Super-resolution via Diffusion Inversion
- 8.19k
Kolors Virtual Try-On
πOverlay garment on person image
- 421
Depth Anything V2
πGenerate depth maps from images
- 402
Stable Point-Aware 3D
β‘Create 3D models from images
- 162
Gaze Demo
πGaze detection using Moondream
- 162
ViTPose Transformers
β‘Detect and annotate poses in images and videos
- 135
Distill Any Depth
π»Generate depth maps from images
- 145
WeShopAI Virtual Try On
πTransform flat-lay shots into on-model photos
- 363
Stable Virtual Camera
β‘Generate virtual camera views from input images