⚠️ This is a img2img only model — text2img will not workdepth2img preserves the overall form of an image by using auto-generated depth maps.See screenshots. Often you can get amazing results with very simple prompts.Tips:<ul><li>Set Denoising strength = 1 (unless you want to save colors from original image)</li><li>512x512 resolution</li><li>Best works with volumetric images: 3D renders, photos</li><li>Not very good with flat colored 2D art </li></ul>

depth2img pruned

Original model: <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-2-depth">https://huggingface.co/stabilityai/stable-diffusion-2-depth</a>I pruned it to float16 so it doesn't crash a1111 in google colab now.The yaml is v2-midas-inference: <a target="_blank" rel="ugc" href="https://raw.githubusercontent.com/Stability-AI/stablediffusion/main/configs/stable-diffusion/v2-midas-inference.yaml">https://raw.githubusercontent.com/Stability-AI/stablediffusion/main/configs/stable-diffusion/v2-midas-inference.yaml</a>

Files with SHA256: 9047a345184eebe77ab91c591422892603a1176991669916a5cbe0bb56f000e6