Forum Replies Created
-
Posts
-
Thank you for the response. Yes, the SDXL Canny works great. For standard, normal camera, architectural visualization-style images, 3 out of 5 pictures are almost perfect. However, I encounter problems with aerial views; sometimes, swimming pools appear on the solarium or roof of the villas, which is amusing. Therefore, I need some form of semantic control in addition to Canny for those views. It also has to be simple enough so I can implement it into an app that can be accessed via API. This way, the architects and technical department can simply input a reference and receive a batch of images without having to use prompts.
What is the best way to train a LoRA locally?, what about textual inversion? at home i have an RTX 3080ti 12GBÂ and in my secondary pc a RTX 3060 12gb, looking to buy a new RTX 4080 Super 16GB for main pc, at work i have an ex mining rig with 5 x RTX 3060 12GB, can i use multi gpu?. Thanks.
Best regads.
Jesus
Hi from Spain. My name is Jesus, i use Anaconda and Python for gaussian splatter, then LM studio for LLM and now stable diffusion, i am a system engineer and developer in unity, unreal, AR, VR, 3D modeler in max, blender, etc., I work for a group of companies that have real estate, golf courses and clothing stores. I want to train Stable Diffusion to use our style of architectural construction and materials, I am open to suggestions. Thanks.
Best regards.
Jesus.
