Hugging Face's logo

nitrosocke
/
Future-Diffusion

Text-to-Image
Diffusers
English
StableDiffusionPipeline
stable-diffusion
Model card Files Community
23
Future-Diffusion / README.md
nitrosocke's picture
nitrosocke
Update README.md
88a7d03
preview code
|
raw
history blame
2.27 kB
metadata
license: openrail++
language:
  - en
tags:
  - stable-diffusion
  - text-to-image
  - diffusers
thumbnail: >-
  https://huggingface.co/nitrosocke/Ghibli-Diffusion/resolve/main/images/ghibli-diffusion-thumbnail.jpg
inference: false

Future Diffusion

This is the fine-tuned Stable Diffusion 2.0 model trained on high quality 3D images with a futuristic Sci-Fi theme. Use the tokens
future style
in your prompts for the effect. Trained on Stability.ai's Stable Diffusion 2.0 Base with 512x512 resolution.

If you enjoy my work and want to test new models before release, please consider supporting me Become A Patreon

Disclaimer: The SD 2.0 model is just over 24h old at this point and we still need to figure out how it works exactly. Please view this as an early prototype and experiment with the model.

Characters rendered with the model: Characters Samples Cars and Animals rendered with the model: Misc. Samples Landscapes rendered with the model: Landscape 1

Prompt and settings for the Characters:

future style [subject] Negative Prompt: duplicate heads bad anatomy
Steps: 20, Sampler: Euler a, CFG scale: 7, Size: 512x704

Prompt and settings for the Landscapes:

future style city market street level at night Negative Prompt: blurry fog soft
Steps: 20, Sampler: Euler a, CFG scale: 7, Size: 1024x576

This model was trained using the diffusers based dreambooth training by ShivamShrirao using prior-preservation loss and the train-text-encoder flag in 7.000 steps.

License

This model is open access and available to all, with a CreativeML Open RAIL++-M License further specifying rights and usage. Please read the full license here