metadata

language:
  - en
thumbnail: https://staticassetbucket.s3.us-west-1.amazonaws.com/outputv2_grid.png
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
datasets:
  - lambdalabs/naruto-blip-captions

Naruto diffusion

Stable Diffusion fine tuned on Naruto by Lambda Labs.

Try the live text-to-naruto demo here!
If you want more details on how to train your own Stable Diffusion variants, see this example.

About

Put in a text prompt and generate your own Naruto style image!

"Bill Gates with a hoodie", "John Oliver with Naruto style", "Hello Kitty with Naruto style", "Lebron James with a hat", "Mickael Jackson as a ninja", "Banksy Street art of ninja"

Prompt engineering matters

We find that prompt engineering does help produce compelling and consistent Naruto style portraits. For example, writing prompts such as ' ninja portrait' or ' in the style of Naruto tends to produce results that are closer to the style of Naruto character with the characteristic headband and other elements of costume.

Here are a few examples of prompts with and without prompt engineering that will illustrate that point.

Bill Gates:

Without prompt engineering

With prompt engineering

A cute bunny:

Without prompt engineering

With prompt engineering

Usage

To run model locally:

!pip install diffusers==0.3.0
!pip install transformers scipy ftfy

import torch
from diffusers import StableDiffusionPipeline
from torch import autocast

pipe = StableDiffusionPipeline.from_pretrained("lambdalabs/sd-naruto-diffusers", torch_dtype=torch.float16)  
pipe = pipe.to("cuda")

prompt = "Yoda"
scale = 10
n_samples = 4

# Sometimes the nsfw checker is confused by the Naruto images, you can disable
# it at your own risk here
disable_safety = False

if disable_safety:
  def null_safety(images, **kwargs):
      return images, False
  pipe.safety_checker = null_safety

with autocast("cuda"):
  images = pipe(n_samples*[prompt], guidance_scale=scale).images

for idx, im in enumerate(images):
  im.save(f"{idx:06}.png")

Model description

Trained on BLIP captioned Naruto images using 2xA6000 GPUs on Lambda GPU Cloud for around 30,000 step (about 12 hours, at a cost of about $20).

Links

Trained by Eole Cervenka after the work of Justin Pinkney (@Buntworthy) at Lambda Labs.