All images in the previews of all my models are made without embeddings, lora's, adetailer or controlnet. Just a prompt and highres fix at 0.3 denoise. I use: CLIP 1 No baked in vae, I myself use: <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/sd-vae-ft-mse-original/tree/main">https://huggingface.co/stabilityai/sd-vae-ft-mse-original/tree/main</a> Feel free to use your own prefered vae!

Nothing Semi-Real

This is the first version of the Semi-realistic branch of Nothing V2.3

Files with SHA256: 364401a4f1f4f5ec318f079bdfa13509aaacae994ca6c628a2ebd7fb9de78e84