the result is not as good as the result in demo

[Qiu-ml]

trafficstars

What are the parameters in the demo? Why can't I get the good result showed in the demo even though I used the same image? Does using different models make a big difference to the results?

[Jack-bo1220]

same question

[guowei-lmars]

same question

[lujiazho]

It seems that the demo result of "Everything" is obtained by using prompts around the whole image, which is different from using mask_generator = SamAutomaticMaskGenerator(sam) in the code.

[Jack-bo1220]

It seems that the demo result of "Everything" is obtained by using prompts around the whole image, which is different from using mask_generator = SamAutomaticMaskGenerator(sam) in the code.

Is there any example code that achieves the same effect as in the web demo “Everything”?

[aooating]

same question

[MiaoJieF]

same question

[welen-zhou]

same question

[1191658517]

same question

[Sindhuja365]

Yes

[TinyAway]

same question

[mulinhu]

same question

[GuoleiSun]

same question

[dmxj]

same question

[DESEOUMAIGA]

same question

[Topdu]

same question

[yong2khoo-lm]

+1 Same

[helen1c]

+1, following

[HettyPatel]

+1

[xyjin01]

+1, following

[HolmesJJ]

+1

[borgarpa]

+1

[Xinghanzzy]

+1

[AlessandroMondin00]

+1

[JunsionGu]

+1

[weiyuemin]

same question

[pyni]

+1

[yuchen-ji]

+1

[hadariru]

+1