malhajar/stable-diffusion-v1-5-ataturk

Stable Diffusion v1-5 atatürk Model Card

The Stable-Diffusion-v1-5-ataturk is a stable-diffusion-v1-5 finetuned on Gazi Mustafa Kemal Ataturk's Photos using dreambooth finetuning.

Example Usuage

First make sure to run the following library installations

pip install -qq git+https://github.com/ShivamShrirao/diffusers

To run interference and get back a photo of Mustafa Kemal Ataturk please run the following code and make sure to include "zwx"

import torch
from torch import autocast
from diffusers import StableDiffusionPipeline, DDIMScheduler

model_path = "malhajar/stable-diffusion-v1-5-ataturk"

pipe = StableDiffusionPipeline.from_pretrained(model_path)
pipe.scheduler = DDIMScheduler.from_config(pipe.scheduler.config)


prompt = "zwx in a military suit, 4k resolution" 
negative_prompt = "white robe, easynegative, bad-hands-5, grainy, low-res, extra limb, poorly drawn hands, missing limb, blurry, malformed hands, blur" 
num_samples = 4 
guidance_scale = 8 
num_inference_steps = 40 
height = 512 
width = 512 

images = pipe(
        prompt,
        height=height,
        width=width,
        negative_prompt=negative_prompt,
        num_images_per_prompt=num_samples,
        num_inference_steps=num_inference_steps,
        guidance_scale=guidance_scale
    ).images
# Save Generated Images
count = 1
for image in images:
    image.save(f"img-{count}.png")
    count += 1

Example Photos:

Model Details

• Finetuned by: Mohamad Alhajar
• Model type: Diffusion-based text-to-image generation model
• Language(s): English
• License: The CreativeML OpenRAIL M license is an Open RAIL M license, adapted from the work that BigScience and the RAIL Initiative are jointly carrying in the area of responsible AI licensing. See also the article about the BLOOM Open RAIL license on which our license is based.
• Model Description: This is a model that can be used to generate and modify images based on text prompts. It is a Latent Diffusion Model that uses a fixed, pretrained text encoder (CLIP ViT-L/14) as suggested in the Imagen paper.

Uses

Misuse, Malicious Use, and Out-of-Scope Use

Note: This section is taken from the DALLE-MINI model card, but applies in the same way to Stable Diffusion v1.

The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.

Out-of-Scope Use

The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.

Misuse and Malicious Use

Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:

• Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
• Intentionally promoting or propagating discriminatory content or harmful stereotypes.
• Impersonating individuals without their consent.
• Sexual content without consent of the people who might see it.
• Mis- and disinformation
• Representations of egregious violence and gore
• Sharing of copyrighted or licensed material in violation of its terms of use.
• Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.

Limitations and Bias

Limitations

• The model does not achieve perfect photorealism
• The model cannot render legible text
• The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
• Faces and people in general may not be generated properly.
• The model was trained mainly with English captions and will not work as well in other languages.
• The autoencoding part of the model is lossy
• The model was trained on a large-scale dataset LAION-5B which contains adult material and is not fit for product use without additional safety mechanisms and considerations.
• No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data. The training data can be searched at https://rom1504.github.io/clip-retrieval/ to possibly assist in the detection of memorized images.

Bias

While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. Stable Diffusion v1 was trained on subsets of LAION-2B(en), which consists of images that are primarily limited to English descriptions. Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. This affects the overall output of the model, as white and western cultures are often set as the default. Further, the ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.

Safety Module

The intended use of this model is with the Safety Checker in Diffusers. This checker works by checking model outputs against known hard-coded NSFW concepts. The concepts are intentionally hidden to reduce the likelihood of reverse-engineering this filter. Specifically, the checker compares the class probability of harmful concepts in the embedding space of the CLIPTextModel after generation of the images. The concepts are passed into the model with the generated image and compared to a hand-engineered weight for each NSFW concept.