Of course Mo could take the high road and build a stable diffusion pipeline using Huggingface’s Diffusers library… But let’s not kid ourselves. Thanks to Automatic1111’s API Mo can duct tape together Houdini and WebUI to use both of these awe inspiring powerful tools to generate… dog images. Welcome to the brave new world that is design!
I’m running into a problem where Houdini 19.5 wants Python 3.9, but Stable Diffusion wants Python 3.10.6. I have some environment variables set, so I just edit those if I want 3.9 or 3.10.6, depending on what I want to play with. How are you handling these version differences? Are you running SD on a virtual environment and leave the OS environment variables set for Houdini?
Cheers
Hey Mo, thank you for this fun excursion. I managed (after many crashes) to get this running on Mac. Wheee! My question if you care to answer: How do I restart the generation process with a new prompt? Or is that being answered in one of the newer videos?