SD V1 5 Cloned

🚀 Stable Diffusion v1-5 Model Card

Stable Diffusion is a latent text-to-image diffusion model that can generate photo-realistic images from any text input. For more details on how it works, refer to 🤗's Stable Diffusion blog.

🚀 Quick Start

Stable Diffusion can generate high - quality images based on text prompts. You can use it with the 🧨Diffusers library or the RunwayML GitHub repository.

✨ Features

• Powerful Image Generation: Capable of generating photo - realistic images from text input.
• Multiple Usage Methods: Can be used with different libraries and repositories.

📦 Installation

Diffusers

You can use the following code to set up the model with the Diffusers library:

from diffusers import StableDiffusionPipeline
import torch

model_id = "runwayml/stable-diffusion-v1-5"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16, revision="fp16")
pipe = pipe.to(device)

prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]  
    
image.save("astronaut_rides_horse.png")

For more detailed instructions, use - cases and examples in JAX, follow the instructions here.

Original GitHub Repository

1. Download the weights:
   • v1 - 5 - pruned - emaonly.ckpt - 4.27GB, ema - only weight. Uses less VRAM, suitable for inference.
   • v1 - 5 - pruned.ckpt - 7.7GB, ema + non - ema weights. Uses more VRAM, suitable for fine - tuning.
2. Follow instructions here.

💻 Usage Examples

Basic Usage

# Use the Diffusers library to generate an image
from diffusers import StableDiffusionPipeline
import torch

model_id = "runwayml/stable-diffusion-v1-5"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16, revision="fp16")
pipe = pipe.to(device)

prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]  
    
image.save("astronaut_rides_horse.png")

📚 Documentation

Model Details

Uses

Direct Use

The model is for research purposes. Possible research areas and tasks include:

• Safe deployment of models that can generate harmful content.
• Probing and understanding the limitations and biases of generative models.
• Generation of artworks and use in design and other artistic processes.
• Applications in educational or creative tools.
• Research on generative models.

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

⚠️ Important Note

This section is taken from the DALLE - MINI model card, but applies to Stable Diffusion v1 as well.

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

Out - of - Scope Use

The model was not trained to provide factual or true representations of people or events. So, using it to generate such content is beyond its capabilities.

Misuse and Malicious Use

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

• Generating demeaning, dehumanizing, or harmful representations of people, their environments, cultures, religions, etc.
• Intentionally promoting or propagating discriminatory content or harmful stereotypes.
• Impersonating individuals without consent.
• Sexual content without the consent of those who might see it.
• Mis - and disinformation.
• Representations of egregious violence and gore.
• Sharing 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 doesn't achieve perfect photorealism.
• It can't render legible text.
• It performs poorly on complex tasks involving compositionality, like rendering an image of “A red cube on top of a blue sphere”.
• Faces and people may not be generated properly.
• Trained mainly with English captions, it works less well in other languages.
• The autoencoding part of the model is lossy.
• Trained on LAION - 5B, which contains adult material, it's not suitable for product use without additional safety mechanisms.
• No deduplication measures were used on the dataset, leading to some memorization of duplicate images. The training data can be searched at [https://rom1504.github.io/clip - retrieval/](https://rom1504.github.io/clip - retrieval/) to detect memorized images.

Bias

Image generation models can reinforce or exacerbate social biases. Stable Diffusion v1 was trained on subsets of LAION - 2B(en), mainly with English descriptions. Texts and images from non - English communities are under - represented, affecting the output. The model performs worse with non - English prompts.

Safety Module

The model is intended to be used with the Safety Checker in Diffusers. This checker compares model outputs against known hard - coded NSFW concepts in the embedding space of the CLIPTextModel after image generation. The concepts are hidden to prevent reverse - engineering.

Training

Training Data

The model was trained on the following dataset:

• LAION - 2B (en) and its subsets.

Training Procedure

Stable Diffusion v1 - 5 is a latent diffusion model combining an autoencoder and a diffusion model trained in the autoencoder's latent space. During training:

• Images are encoded into latent representations by an encoder. The autoencoder has a relative downsampling factor of 8, mapping H x W x 3 images to H/f x W/f x 4 latents.
• Text prompts are encoded by a ViT - L/14 text - encoder.
• The non - pooled output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross - attention.
• The loss is a reconstruction objective between the added noise and the UNet's prediction.

There are currently six Stable Diffusion checkpoints, trained as follows:

• stable - diffusion - v1 - 1: 237,000 steps at 256x256 on [laion2B - en](https://huggingface.co/datasets/laion/laion2B - en), then 194,000 steps at 512x512 on [laion - high - resolution](https://huggingface.co/datasets/laion/laion - high - resolution).

• stable - diffusion - v1 - 2: Resumed from stable - diffusion - v1 - 1, 515,000 steps at 512x512 on "laion - improved - aesthetics".

• stable - diffusion - v1 - 3: Resumed from stable - diffusion - v1 - 2, 195,000 steps at 512x512 on "laion - improved - aesthetics" with 10% text - conditioning dropping.

• stable - diffusion - v1 - 4: Resumed from stable - diffusion - v1 - 2, 225,000 steps at 512x512 on "laion - aesthetics v2 5+" with 10% text - conditioning dropping.

• stable - diffusion - v1 - 5: Resumed from stable - diffusion - v1 - 2, 595,000 steps at 512x512 on "laion - aesthetics v2 5+" with 10% text - conditioning dropping.

• stable - diffusion - inpainting: Resumed from stable - diffusion - v1 - 5, 440,000 steps of inpainting training at 512x512 on “laion - aesthetics v2 5+” with 10% text - conditioning dropping.

• Hardware: 32 x 8 x A100 GPUs

• Optimizer: AdamW

• Gradient Accumulations: 2

• Batch: 32 x 8 x 2 x 4 = 2048

• Learning rate: Warmed up to 0.0001 for 10,000 steps and then kept constant.

Evaluation Results

Evaluations were conducted with different classifier - free guidance scales (1.5, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0) and 50 PNDM/P

📄 License

This model is open access under a CreativeML OpenRAIL - M license.

1. You can't use it to deliberately produce or share illegal or harmful outputs.
2. CompVis has no rights over the outputs you generate. You're free to use them but accountable for their proper use as per the license.
3. You may redistribute the weights and use the model commercially or as a service, but you must include the same use restrictions and share a copy of the CreativeML OpenRAIL - M license with all users. Read the full license here. By accessing the repository, you consent to sharing your contact information (email and username) with the model authors.