![](https://replicate.delivery/pbxt/ofleflEMbUCZ8JZLJrw4EDYi7dRsB0G5dBjyAGbcUJliiBKlA/remove_bg_390.png)
zylim0702/remove_bg
Best Human detection and Object Detection Background removal.
![](https://tjzk.replicate.delivery/models_models_cover_image/1a9d0046-4204-4c10-ac29-82830256a87f/bokeh_neural.png)
zylim0702/bokeh_prediction
Bokeh Prediction, a hybrid bokeh rendering framework that combines a neural renderer with a classical approach. It generates high-resolution, adjustable bokeh effects from a single image and potentially imperfect disparity maps.
zylim0702/stable-diffusion-xl-base-1.0-inpainting
Stable diffusion XL with flexible image width and height
![](https://tjzk.replicate.delivery/models_models_cover_image/363fdcf5-234f-4311-b6f0-db72bbe33395/replicate-prediction-otxlnltb2va7.png)
zylim0702/controlnet-v1-1-multi
clip interrogator with controlnet sdxl for canny and controlnet v1.1 for the others
![](https://tjzk.replicate.delivery/models_models_cover_image/66942682-c7da-4722-a281-3ffe40659a90/replicate-prediction-y2ajw3tb5n7d.png)
zylim0702/sdxl-lora-customize-training
Introducing a Lora Instant Training model for crafting stunning 1024x1024 visuals. Train your own Lora Model via zip photos for instant outputs. Try Lora Model using this link: https://replicate.com/zylim0702/sdxl-lora-customize-model.
![](https://replicate.delivery/pbxt/nSoKenfp8aqFTkQ4qcDeifAOKbPXeRarzT6fj3I1cm6zI99WE/out-3.png)
zylim0702/sdxl-lora-customize-model
Introducing a text-to-image AI that crafts stunning 1024x1024 visuals. Load LoRa models via URLs for instant outputs. Train using this link: https://replicate.com/zylim0702/sdxl-lora-customize-training.
zylim0702/remove-object-large
zylim0702/multi_controlnet_inpainting_stable_diffusion
zylim0702/sd_inpaint_vlpart_any_part
zylim0702/lang_sam_inpainting
zylim0702/low_light_enhancer
![](https://replicate.delivery/pbxt/SFZnhwaRO1rVCNNPYSpEL0LyBa4fsMjXKqbHfV4A0XBffQpFB/seed-6400.png)
zylim0702/qr_code_controlnet
ControlNet QR Code Generator: Simplify QR code creation for various needs using ControlNet's user-friendly neural interface, making integration a breeze. Just key in the url !
zylim0702/make-up-transfer
![](https://replicate.delivery/pbxt/9neVICdX2hw2KaMKPOGey6bRfyN5pyMuMGqhGQYwwvcBTzmiA/remove_anthing.png)
zylim0702/remove-object
The LaMa (Large Mask Inpainting) model is an advanced image inpainting system designed to address the challenges of handling large missing areas, complex geometric structures, and high-resolution images.