Darksoulsdiffusion

🚀 DarkSouls Diffusion

This is a Dreamboothed Stable Diffusion model trained on the DarkSouls series Style, enabling text-to-image and image-to-image generation.

This is a Dreamboothed Stable Diffusion model trained on the DarkSouls series Style. The total dataset is made of 100 pictures, and the training has been done on runawayml 1.5 and the new VAE, with 2500 steps (LR1e-6) then 24k more steps (LR1e-7). The token "DarkSouls Style" will bring in the new concept. The recommended sampling is k_Euler_a or DPM++ 2M Karras on 20 steps, CFGS 7.

CKPT download link

🚀 Quick Start

This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion.

You can also export the model to ONNX, MPS and/or FLAX/JAX.

✨ Features

• Stable Diffusion: This model is based on Stable Diffusion, supporting text-to-image and image-to-image generation.
• DarkSouls Style: Trained on the DarkSouls series style, using the token "DarkSouls Style" can introduce this new concept.
• Diverse Sampling: The recommended sampling methods are k_Euler_a or DPM++ 2M Karras with specific step and CFG settings.

💻 Usage Examples

Basic Usage

from diffusers import StableDiffusionPipeline
import torch

model_id = "Guizmus/DarkSoulsDiffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "a soldier engulfed in fire, DarkSouls Style"
image = pipe(prompt).images[0]

image.save("./DarkSouls Style.png")

📄 License

This model is licensed under the creativeml-openrail-m license.