Sd Xl Alternative Bases

🚀 Alternative Stable Diffusion XL Base 1.0 Models

This repository offers alternative or tuned versions of Stable Diffusion XL Base 1.0 in .safetensors format, facilitating various text - to - image generation tasks.

🚀 Quick Start

This repository contains alternative or tuned versions of Stable Diffusion XL Base 1.0 in .safetensors format.

✨ Features

• Multiple Model Variants: Offers different versions of Stable Diffusion XL Base 1.0, including merged models with specific VAEs and inpainting capabilities.
• Inpainting Calculation Formula: Provides a formula to create an SDXL inpainting checkpoint from any SDXL checkpoint.

📦 Available Models

sd_xl_base_1.0_fp16_vae.safetensors

This file contains the weights of sd_xl_base_1.0.safetensors, merged with the weights of sdxl_vae.safetensors from MadeByOllin's SDXL FP16 VAE repository.

sd_xl_base_1.0_inpainting_0.1.safetensors

This file contains the weights of sd_xl_base_1.0_fp16_vae.safetensors merged with the weights from diffusers/stable-diffusion-xl-1.0-inpainting-0.1.

💻 Usage Examples

Creating an SDXL Inpainting Checkpoint

Using the .safetensors files here, you can calculate an inpainting model using the formula A + (B - C), where:

• A is sd_xl_base_1.0_inpainting_0.1.safetensors
• B is your fine - tuned checkpoint
• C is sd_xl_base_1.0_fp16_vae.safetensors

Using ENFUGUE's Web UI:

⚠️ Important Note

You must specifically use the two files present in this repository for this to work. The Diffusers team trained XL Inpainting using FP16 XL VAE, so using a different XL base will result in an incorrect delta being applied to the inpainting checkpoint, and the resulting VAE will be nonsensical.

📚 Documentation

Model Description

Uses

Direct Use

The model is intended for research purposes only. Possible research areas and tasks include:

• Generation of artworks and use in design and other artistic processes.
• Applications in educational or creative tools.
• Research on generative models.
• Safe deployment of models which have the potential to generate harmful content.
• Probing and understanding the limitations and biases of generative models.

Out - of - Scope Use

The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out - of - scope for the abilities of this model.

Limitations and Bias

Limitations

• The model does not achieve perfect photorealism.
• The model cannot render legible text.
• The model struggles with more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”.
• Faces and people in general may not be generated properly.
• The autoencoding part of the model is lossy.
• When the strength parameter is set to 1 (i.e. starting in - painting from a fully masked image), the quality of the image is degraded. The model retains the non - masked contents of the image, but images look less sharp. We're investing this and working on the next version.

Bias

While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.

📄 License

The models in this repository are licensed under the CreativeML Open RAIL++ - M License.