More Adobe Substance Modeler +AI experiments. Using quick, gestural 3d sketching to drive generative AI with much higher levels of creative control than you could ever get from a text prompt alone. The more detailed your 3d model is, the more you can leave the ai to just finish details like skin texture and individual strands of hair.. my model is obviously just a quick sketch #art #ai

Details on the process: I sculpt the basic 3d model in Adobe Substance 3D Modeler, using both the non-VR and VR mode of working. I use Krea AI and screen2image to feed the i mage from Modeler, into Krea. Here, I can transform the input image using a text prompt and the AI strength slider. The more detailed your model is, the less AI hallucination you need, which in my mind is where we need to move towards for a really interesting combination of the strength of human creativity AND ai. Once I get an AI version of my model that I feel is close to my creative idea, I send that image to Tripo Ai where the image is converted to a 3d model in a matter of seconds. I then bring that back to Modeler for more refinement. Once I'm happy with the model, I light and compose the scene in Marmoset Toolbag. I'm using Marmoset because of how easy it is to setup my scene here.. it's responsive, realtime and it looks good. The small animated clips are made using Runway and Leonardo Ai.