models compvis stable diffusion v1 4

compvis-stable-diffusion-v1-4

Overview

Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input. The Stable-Diffusion-v1-4 checkpoint was initialized with the weights of the Stable-Diffusion-v1-2 checkpoint and subsequently fine-tuned on 225k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve classifier-free guidance sampling.

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

Safe deployment of models which have the potential to 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.

Stable Diffusion DreamBooth Finetuning is now avalable for this model on AzureML. DreamBooth is a method for personalizing text-to-image models. It fine-tunes these models using 5-10 images of a specific subject, allowing them to generate personalized images based on textual 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.

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.

Training Details

Training Data

The model developers used the following dataset for training the model:

LAION-2B (en) and subsets thereof (see next section)

Training Procedure

Stable Diffusion v1-4 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,

Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
Text prompts are encoded through 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 noise that was added to the latent and the prediction made by the UNet.

We currently provide following checkpoint, which was trained as follows.

stable-diffusion-v1-4 Resumed from stable-diffusion-v1-2.225,000 steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to improve classifier-free guidance sampling.
Hardware: 32 x 8 x A100 GPUs
Optimizer: AdamW
Gradient Accumulations: 2
Batch: 32 x 8 x 2 x 4 = 2048
Learning rate: warmup to 0.0001 for 10,000 steps and then kept constant

Evaluation Results

Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling steps show the relative improvements of the checkpoints:

pareto

Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores.

Limitations and Biases

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.

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.

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.

DreamBooth Finetuning Samples

Task	Use case	Dataset	Python sample (Notebook)	CLI with YAML
Text-to-image	Text-to-image	dog-example	diffusers-dreambooth-dog-text-to-image.ipynb	diffusers-dreambooth-dog-text-to-image.sh

Inference Samples

Note: The inferencing script of this model is optimized for high-throughput, low latency using Deepspedd-mii library. Please use version 4 of this model for inferencing using default (FP32) diffusion pipeline implementation.

Inference type	Python sample (Notebook)	CLI with YAML
Real time	text-to-image-online-endpoint.ipynb	text-to-image-online-endpoint.sh
Batch	text-to-image-batch-endpoint.ipynb	text-to-image-batch-endpoint.sh

Inference with Azure AI Content Safety (AACS) samples

Inference type	Python sample (Notebook)
Real time	safe-text-to-image-online-deployment.ipynb
Batch	safe-text-to-image-batch-endpoint.ipynb

Sample input and output

Supported Parameters

num_inference_steps: The number of de-noising steps. More de-noising steps usually lead to a higher quality image at the expense of slower inference, defaults to 50.
guidance_scale: A higher guidance scale value encourages the model to generate images closely linked to the text prompt at the expense of lower image quality. Guidance scale is enabled when guidance_scale > 1, defaults to 7.5.

These parameters are optional inputs. If you need support for new parameters, please file a support ticket.

Sample input

{
   "input_data": {
        "columns": ["prompt"],
        "data": ["a photograph of an astronaut riding a horse", "lion holding hunted deer in grass fields"],
        "index": [0, 1],
        "parameters": {
            "num_inference_steps": 50,
            "guidance_scale": 7.5
        }
    }
}

Sample output

[
    {
        "prompt": "a photograph of an astronaut riding a horse",
        "generated_image": "image1",
        "nsfw_content_detected": false
    },
    {
        "prompt": "lion holding hunted deer in grass fields",
        "generated_image": "image2",
        "nsfw_content_detected": true
    }
]

Note:

"image1" and "image2" strings are base64 format.

If "nsfw_content_detected" is True then generated image will be totally black.

Visualization for the prompt - "a photograph of an astronaut riding a horse"

compvis_stable_diffusion_v1_4 visualization

Version: 11

Wiki menu

Home
Reference Documentation
- Components
- Data
- Environments
- Models
Contributing

Provide feedback

Saved searches

Use saved searches to filter your results more quickly