pony-diffusion-v4 - "same, but different" edition

pony-diffusion is a latent text-to-image diffusion model that has been conditioned on high-quality pony, furry and other non photorealistic images through fine-tuning.

WARNING: This model is capable of producing NSFW content so it's recommended to use 'safe' tag in prompt in combination with negative prompt for image features you may want to suppress (i.e. nudity).

Despite its name, this model is capable of producing wide range of furry and cartoon images as side effect of improving data diversity (with exception of anime stlyes, for which Waifu Diffusion is much stronger choice).

Special thanks to Waifu-Diffusion for providing finetuning expertise and advising through the process, without their help this project would not exist.

Pruned safetensors PyTorch Model (use this with Automatic1111 or other SD UIs)

Automatic1111 colab and Diffusers colab

Please join PurpleSmartAI Discord to use this model with our free SD bot and get early access to models in development.

You can see more samples at PurpleSmartAI

Model Description

The model originally used for fine-tuning is Stable Diffusion V1-5, which is a latent image diffusion model trained on LAION2B-en.

This particular checkpoint has been fine-tuned with a learning rate of 5.0e-6 for 15 epochs on approximately 3M pony, furry and other cartoon text-image pairs (using metadata from derpibooru, e621 and danbooru).

Improvements over previous models

Better disentanglement of tag based prompts

Aka "using Hidden States of CLIP’s Penultimate Layer", a technique adopted by SD2 which should lead to generally higher quality and more tag driven outputs.

Compared to pony-diffusion-v3 using penultimate CLIP is generally the best choice but trying both CLIP skip of 1 and 2 is still recommended.

Improved data quality labeling

We reccomend adding 'derpibooru_p_95' to prompt and 'derpibooru_p_low' to negative prompt to improve quality of generated pony images.

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

Downstream Uses

This model can be used for entertainment purposes and as a generative art assistant.

Example Code

import torch
from torch import autocast
from diffusers import StableDiffusionPipeline, DDIMScheduler
model_id = "AstraliteHeart/pony-diffusion-v4"
device = "cuda"
pipe = StableDiffusionPipeline.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    revision="fp16",
    scheduler=DDIMScheduler(
        beta_start=0.00085,
        beta_end=0.012,
        beta_schedule="scaled_linear",
        clip_sample=False,
        set_alpha_to_one=False,
    ),
)
pipe = pipe.to(device)
prompt = "pinkie pie anthro portrait wedding dress veil intricate highly detailed digital painting artstation concept art smooth sharp focus illustration Unreal Engine 5 8K"
with autocast("cuda"):
    image = pipe(prompt, guidance_scale=7.5)["sample"][0]  
    
image.save("cute_poner.png")

Team Members and Acknowledgements

This project would not have been possible without the incredible work by the CompVis Researchers.

• Waifu-Diffusion for helping with finetuning

In order to reach us, you can join our Discord server.