How to set up SDXL 0.9 locally (stable-diffusion-xl-base-0.9 Diffusion-based text-to-image generative AI model)
How to set up SDXL 0.9 locally (stable-diffusion-xl-base-0.9 Diffusion-based text-to-image generative AI model)
medium.com How to set up SDXL 0.9
Download from https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9 . You can fill out the form with anything.
2
comments
Adding the refiner to stable-diffusion-xl-base-0.9:
- Download sd_xl_refiner_0.9.safetensors from https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-0.9/tree/main
- copy sd_xl_refiner_0.9.safetensors to \ComfyUI_windows_portable\ComfyUI\models\checkpoints .
- Download https://github.com/camenduru/sdxl-colab/blob/main/refiner.json
- Load refiner.json with ComfyUI
- Download from https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9 . You can fill out the form with anything.
- Download ComfyUI from https://github.com/comfyanonymous/ComfyUI .
- Unzip ComfyUI.
- Copy the downloaded sd_xl_base_0.9.safetensors to \ComfyUI_windows_portable\ComfyUI\models\checkpoints .
- Run run_nvidia_gpu.bat .
- Change both width and height under Empty Latent Image to 1024.
- At Ksampler Change the sampler name to dpmpp_2s_ancestral
- Enter positive prompt
- Enter negative prompt (optional)