Playground v2.5 model generates images based on text prompts. It is a Latent Diffusion Model that uses two fixed, pre-trained text encoders (OpenCLIP-ViT/G and CLIP-ViT/L). It follows the same architecture as Stable Diffusion XL.

1. update comfyui

2. download checkpoint:  https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic/blob/main/playground-v2.5-1024px-aesthetic.fp16.safetensors

(comfyui/models/checkpoints)

Playground v2.5 is not suitable for generating real-life photos. The skin texture has no details and the hair is not realistic.