ComfyUI-3D-Pack icon indicating copy to clipboard operation
ComfyUI-3D-Pack copied to clipboard

3 or 4 3d image view instead of one

Open kakachiex2 opened this issue 1 year ago • 4 comments

It is possible to use generate image view instead of one to get a more detailed model for example see this model on Civita I think create a workflow with this approach will be much accurate to use only one image view :

  • Civitai Lora : https://civitai.com/models/291056/fn-collectionipxl-creative-three-views
  • Some examples :

04785-1287753445-IP,anime characters,slim figure,hand version style,girl,Three views,lora_FN-CollectionIP_XL-V1 0_0 8,lace short-sleeve top,(Pr 00319-1948818482 04755-680405229-front,back,side,three view,glass mimicry,girl,glass mimicry ip,describe this image in a very detailed manner  a 3d-rendered char

kakachiex2 avatar Feb 12 '24 21:02 kakachiex2

I'm a 3D Modeler and I found this really interesting specially if I create my own sketch character render it in ComfyUI and generate all the views them generate the 3d model send to Blender and sculpt all details this will be the ultimate workflow..

kakachiex2 avatar Feb 12 '24 21:02 kakachiex2

what is the ideal size this model support 512, 768 or...?

kakachiex2 avatar Feb 12 '24 21:02 kakachiex2

Hi, friend, you can use your own images of 4 angles as others have already asked: Just make input images square, the node will automatically resize the image to the correct input size, for LGM is 256X256 Nice looking images by the way ;)

MrForExample avatar Feb 13 '24 20:02 MrForExample

Thanks for your reply

kakachiex2 avatar Feb 15 '24 08:02 kakachiex2