ComfyUI - Object Detection & Segmentation - Florence2 & SAM2

[@antoniojoaocastrocostajuni8558]

Is it possible to use the model to segment Stable Difusion / Midjourney deformed pictures? (multiple fingers, blurry flaces, etc)

[@MikevomMars]

9:03 - If you want to mask MULTIPLE objects at once (like the two monitors in the video, index 0 and 1) - how would you do this?

[@elifmiami]

Its pretty useful ! How can we do multiple object at the same time ?

[@yngeneer]

thx for that easy video! what if...what if the preview image from 'florence run' is ok, the person is detected correctly, but in the output it masks the skirt only, not the whole person? tried different values in 'max_new_tokens' & 'num_beams' , tried 'woman', 'woman figure', 'female', 'female figure', 'figure', 'dancer'-> without any effect... different video is ok, but in one particular video it just stick with the skirt only ... :(

[@ertbul]

same problem here... by anychance did you find a solution?

[@erans]

What are the minimal requirements? im using 4060ti (16gb gpu ram) and i got a not enough memory error

[@CgTopTips]

Your system meets the minimum requirements (Min is 8gb). you need to adjust the resolution and loaded frames considering the 16GB VRAM !

[@erans]

@@CgTopTips thanks, any way to calculate what size \ length of video i could use? or is it kind of a guessing game?

[@uzivatelInternetu]

Cant see node Florence2Coordinates.

[@CgTopTips]

Are you sure the Florence nod is installed correctly ?

[@uzivatelInternetu]

@@CgTopTips everything is fine now, was my mistake

[@너의그날은역사와함께]

Sir, please take a look at how to make game sprites. thank you for the good video

[@CgTopTips]

Unfortunately, I don't have any experience in game making :(

[@MrDanINSANE]

Thanks for sharing!
- Can you please show how to do it with the new Sam2 Point Editor?
- Also, how to EXPORT ONLY the final selected segment into a video without the background?
Thanks ahead! 🙏

[@abhijeetmaurya6827]

how can we use this cloth swapping ? plzzz tell

[@CgTopTips]

I'll need to explain this in another tutorial video, as it's difficult to cover here. :)

[@abhijeetmaurya6827]

@@CgTopTips yes plz make a video on it waiting for it.....

[@abhijeetmaurya6827]

@@CgTopTips i have made a raw workflow on i like to share to you so you can guide me on it some other thing i also like to know how to add in comfyui

[@zombieploios]

@@CgTopTips + for this would love a tutorial on changing clothing or anything else via some video inpainting method... I m guessing we take all frames as input + mask and generate pics for each frame then put all frames back in video