From 5fb1af46326fb086339c8a87a0e31d8486fd34f0 Mon Sep 17 00:00:00 2001 From: jordddan <1192787158@qq.com> Date: Mon, 26 Jun 2023 15:38:19 +0800 Subject: [PATCH] update --- README.md | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 802db7d1..882cf42b 100644 --- a/README.md +++ b/README.md @@ -13,7 +13,7 @@ See our paper: [Visual ChatGPT: Talking, Drawing and Editing with V ## Updates: -- Now TaskMatrix supports [GroundingDINO](https://github.com/IDEA-Research/GroundingDINO) and [segment-anything](https://github.com/facebookresearch/segment-anything)! Thanks **@jordddan** for his efforts. For the image editing case, `GroundingDINO` is first used to locate bounding boxes guided by given text, then `segment-anything` is used to generate the related mask, and finally stable diffusion inpainting is used to edit image based on the mask. +- Now TaskMatrix supports [GroundingDINO](https://github.com/IDEA-Research/GroundingDINO) and [segment-anything](https://github.com/facebookresearch/segment-anything)! Thanks **@jordddan** for his efforts. For the image editing case, `GroundingDINO` is first used to locate bounding boxes guided by given text, then `segment-anything` is used to generate the related mask, and the masked area will be filled by an inpainting model. - Firstly, run `python visual_chatgpt.py --load "Text2Box_cuda:0,Segmenting_cuda:0,Inpainting_cuda:0,ImageCaptioning_cuda:0"` - Then, say `find xxx in the image` or `segment xxx in the image`. `xxx` is an object. TaskMatrix will return the detection or segmentation result! @@ -130,8 +130,7 @@ Here we list the GPU memory usage of each visual foundation model, you can speci We appreciate the open source of the following projects: [Hugging Face](https://github.com/huggingface)   -[LangChain](https://github.com/hwchase17/langchain)   -[Stable Diffusion](https://github.com/CompVis/stable-diffusion)   +[LangChain](https://github.com/hwchase17/langchain)   [ControlNet](https://github.com/lllyasviel/ControlNet)   [InstructPix2Pix](https://github.com/timothybrooks/instruct-pix2pix)   [CLIPSeg](https://github.com/timojl/clipseg)