Hey! I need to make 2d images in batch.Now i use whisk + plugin.Which do the job pretty well.Now I'm thinking i need to switch to llm.Right now i use omnivoice inside pinokio which is the best voice cloner I've ever seen+ free.So I'm aiming for a text to speech model where i can just place my subject and just add prompts as batch and everything is done automatically.

My pc specs:

AMD Ryzen 5 5600 ​Gigabyte B550M K ​MSI GeForce RTX 3060 VENTUS 2X 12G OC ​Netac Shadow 16GB DDR4 3200MHz (x2) ​Kingston NV3 1TB M.2 NVMe SSD ​Deepcool PL650D 650W ​Deepcool MATREXX 40 3FS