Nitro Diffusion

Nitro Diffusion is a fine-tuned Stable Diffusion model that was trained from scratch on three artstyles simultaneously. It allows for high control of mixing, weighting and single style use, with the tokens "archer style", "arcane style" or "modern disney style" used in prompts to activate the desired effect. This AI model can produce mixed styles as well.

Nitro Diffusion

Welcome to Nitro Diffusion - the first Multi-Style Model trained from scratch! This is a fine-tuned Stable Diffusion model trained on three artstyles simultaniously while keeping each style separate from the others. This allows for high control of mixing, weighting and single style use. Use the tokens archer style, arcane style or modern disney style in your prompts for the effect. You can also use more than one for a mixed style like in the examples down below:

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

Multi Style Characters from the model: Multi Samples Single Style Characters from the model: Single Samples Multi Style Scenes from the model: Misc. Samples

You can find animated GIFs of Batman and Lara Croft showing the weighting and prompt influence on the bottom of the page.

Prompt and settings for Gal Gadot:

arcane archer modern disney gal gadot Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 598801516, Size: 512x768

Prompt and settings for the Audi TT:

(audi TT car) arcane modern disney style archer Steps: 30, Sampler: Euler a, CFG scale: 7, Seed: 713702776, Size: 768x512

Gradio

We support a Gradio Web UI to run Nitro-Diffusion: Open In Spaces

🧨 Diffusers

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 .

from diffusers import StableDiffusionPipeline
import torch

model_id = "nitrosocke/nitro-diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "archer arcane style magical princess with golden hair"
image = pipe(prompt).images[0]

image.save("./magical_princess.png")

License

This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:

  1. You can’t use the model to deliberately produce nor share illegal or harmful outputs or content
  2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
  3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here

Video Demos

Batman

Batman

Lara Croft

Lara Croft

Related Posts

Zayn Malik AI Voice

Zayn Malik AI Voice

Introducing the groundbreaking AI-produced collection of songs by Zayn Malik! Experience a diverse range of styles and languages, made possible by VITS Retrieval-based Voice Conversion methods.

Ariana Grande AI Voice

Ariana Grande AI Voice

Say hello to the future of music with AI Ariana Grande!

Eazy-E AI Voice

Eazy-E AI Voice

Introducing our latest collection of songs by AI Eazy-E! Produced using cutting-edge VITS Retrieval based Voice Conversion methods, this collection includes a diverse range of styles and languages for evaluation purposes.