This repository contains multiple experimental text-to-image models based on Stable Diffusion XL. These models are created by merging pre-trained models that have been fine-tuned on different tasks, such as anime, realism, artistic styles, and prompt adherence.
Key Features
Multiple models: A collection of models with varying specializations. Diverse styles: Experimentation with different artistic styles and image generation tasks.
- AniRealXL: Focuses on anime and surrealism.
- ProteusAniMix: Prioritizes prompt adherence while blending anime and realism styles.
- UnimixXL: A mix of various art models for diverse outputs.
- MixSDXL: Another mix of art models, offering different artistic styles.
- UnimixXL: Specialized in generating artistic images.
- MidSDXL: Aims to replicate Midjourney-like image quality and diverse styles.
Link:
- AniRealXL: Link to AniRealXL model
- ProteusAniMix: Link to ProteusAniMix model
- UnimixXL: Link to UnimixXL model
- MixSDXL: Link to MixSDXL model
- UnimixXL: Link to MixSDXL model
- MidSDXL: Link to MixSDXL model
MidSDXL
Diverse Style
Inference API (serverless) is not available, repository is disabled.