--- license: creativeml-openrail-m tags: - stable-diffusion - stable-diffusion-diffusers - text-to-image inference: false extra_gated_prompt: |- 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 claim 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 carefully here: https://huggingface.co/spaces/CompVis/stable-diffusion-license extra_gated_heading: Please read the LICENSE to access this model --- Models better suited for High-Resolution Image Synthesis. The main model (doohickey/doohickey-mega) has been finetuned from [runwayml/stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) near a resolution of 768x768 for use with Doohickey. Current models: | name | description | datasets used | | --- | --- | --- | | doohickey/doohickey-mega/v1-3000steps.ckpt | first try, rlly good hd, bad results w/ other aspect ratios than 1:1 trained at 704x704 | A-1k| | doohickey/doohickey-mega/v2-3000steps.ckpt | same as last one but worse | A-1k + ~1k samples from LAION-2b-En-Aesthetic >=768x768 | | doohickey/doohickey-mega/v3-3000.ckpt | with new CLIP model ([laion/CLIP-ViT-L-14-laion2B-s32B-b82K](https://hf.co/laion/CLIP-ViT-L-14-laion2B-s32B-b82K)) (CLIP model also finetuned the 3k steps), models past this point were trained with various aspect ratios from 640x640 min to 768x768 max resolution. (examples 768x640 or 704x768) | A-1k + E-10k | | doohickey/doohickey-mega/v3-6000.ckpt | 3k steps on top of v3-3000.ckpt, better at hands! (just UNet finetune, added a RandomHorizontalFlip operation at 50%) | A-1k | | doohickey/doohickey-mega/v3-7000.ckpt | continuation of last model, I thought Colab would crash after 3k steps but it kept going for a little while saving ckpts every 1k steps. | A-1k | | doohickey/doohickey-mega/v3-8000.ckpt | see last description, v3-6000 + 2k steps | A-1k | Datasets: | name | description | status | | --- | --- | --- | | A-1K | 1k scraped images, captioned with BLIP (more refined aesthetic) | private, worried about possible unsafe (nsfw, offensive) images or captions | | E-10k | 10k scraped images captioned with BLIP (less refined aesthetic) | private, worried about possible unsafe (nsfw, offensive) images or captions | _Note this section taken from the Stable Diffusion model card._ # Uses ## Direct Use 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. Excluded uses are described below. ### Misuse, Malicious Use, and Out-of-Scope Use _Note: This section is taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), 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](https://laion.ai/blog/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/](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)](https://laion.ai/blog/laion-5b/), 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](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) 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.