ApacheXL-Dream! v1 by Apache Labs

🎉 Introducing ApacheXL Dream! 🌍 ApacheXL-Dream is designed to generate stunning, photorealistic/dream-like portraits, specifically featuring individuals under natural lighting conditions.

Terms and Conditions: Using this model, you agree not to deploy it behind API services or competing platforms. For commercial licenses, please contact license@apachelabs.com.

This model is not authorised for use in API services. Please contact license@apachelabs.com for business inquiries, commercial licensing, and consultation.

Key Features:

• Exceptional, prompt adherence ✅
• High-quality image generation
• Optimized for generating portraits with freckles
• Enhanced details and compositions
• Trained on an extensive dataset to ensure diverse representation

Experience the power of ApacheXL v1:

• Find CompVis(A1111) for model deployment using A1111.
• Every other file other than CompVis(A1111) is part of Diffusers.

Usage:

Make sure to upgrade diffusers to >= 0.19.0:

pip install diffusers --upgrade

In addition, make sure to install transformers, safetensors, accelerate as well as the invisible watermark:

pip install invisible_watermark transformers accelerate safetensors

To just use the base model, you can run:

from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained("apache-labs/apachexl-dream", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
pipe.to("cuda")
# if using torch < 2.0
# pipe.enable_xformers_memory_efficient_attention()
prompt = "An astronaut riding a green horse"
images = pipe(prompt=prompt).images[0]

Other Sites ApacheXL is on:

• Civit AI

We appreciate your support in our journey to enhance generative AI capabilities. Don't forget to follow us for updates on new models and features:

• Twitter