sd-webui-segment-anything

sd-webui-segment-anything copied to clipboard

The first use case displayed in [Edit Anything's](https://github.com/sail-sg/EditAnything) github repository is a cross image merge in which a reference image is mapped onto an existing image. Is this task supported...

KilianB

请教下sam_dummy_component这个当做前后端传值的组件，大概的原理是怎样的

1

大佬好，感谢你做的贡献。 我再研究你的源码的过程中发现一个点搞不明白，特来请教。 sam.py中你使用了sam_dummy_component = gr.Label(visible=False)这个组件，我大概猜到这个应该是用来存在鼠标点击标注正向和反向两个数组的。 然后再一下点击事件中把sam_dummy_component作为sam_predict函数的参数 sam_submit.click( fn=sam_predict, _js='submit_sam', inputs=[sam_model_name, sam_input_image, # SAM sam_dummy_component, sam_dummy_component, # Point prompts dino_checkbox, dino_model_name, dino_text_prompt, dino_box_threshold, # DINO prompts dino_preview_checkbox, dino_preview_boxes_selection], # DINO preview...

lijun4017

### Expected behavior When --lowvram is enabled the VRAM is being freed after the process is completed. Maybe make an checkbox feature like the ControlNet feature has and we can...

monstari

[Bug]: "Copy to Inpaint Upload & img2img ControlNet Inpainting" is not working >> Solved

1

### Is there an existing issue for this? - [X] I have searched the existing issues and checked the recent builds/commits of both this extension and the webui ### Have...

red-sponge

### Expected behavior Can you add this model to your extension? This would be good, because then you could change the colour, style and other characteristics of the clothes and...

mykeehu

https://github.com/continue-revolution/sd-webui-segment-anything/blob/d80220ecd2151cebfb00a5829be8ec1c05118000/scripts/sam.py#L293C65-L293C65

linhuaiyi

[Feature]: can it install and download a sam model after installing, i work on colab and it dosent seems to be downloading sam

3

### Expected behavior it gives Start SAM Processing Found GroundingDINO in pip. Verifying if dynamic library build success. GroundingDINO dynamic library have been successfully built. Running GroundingDINO Inference Initializing GroundingDINO...

revolverocelot1

HELP ~ GroundingDINO dont work on my mac ~ I got 2 problems

16

### I install the extensions in WebUI by URL, and setup the params in text2img panel, download the SAM Model & GroundingDINO Model, is good so far, till I run...

coong4

groundingDINO box overlay text too tiny to read

1

Has anyone had this issue? I can't see the numbers for each box. 

dangerweenie

I have not been able to figure out how to do batch processing with GroundingDINO. wondering if you can help me.

2

### Expected behavior As title describes, I have only seen the ``` boxes, logits, phrases = predict( model=self.GroundingDINO, image=obs.to(torch.float32), caption=caption or self.caption, box_threshold=0.3, text_threshold=0.25, device=obs.device ) ``` syntax using single...

slerman12