Hugging Face's logo
Jessie Rice's picture
70 8

Jessie Rice

Juno360219
Badladfilms's profile picture 21world's profile picture
·

AI & ML interests

None yet

Organizations

None yet

Juno360219's activity

New activity in google/sdxl 21 days ago

delete files
#1836 opened 21 days ago by Juno360219
New activity in TencentARC/BrushNet about 1 month ago

Delete data/ckpt/realisticVisionV60B1_v51VAE/safety_checker
#3 opened about 1 month ago by Juno360219

Delete data/ckpt/realisticVisionV60B1_v51VAE/safety_checker/pytorch_model.bin
#2 opened about 1 month ago by Juno360219
New activity in AP123/SDXL-Lightning 3 months ago

Delete safety_checker.py
#6 opened 3 months ago by Juno360219

Delete app.py

1
#5 opened 3 months ago by Juno360219
New activity in lambdalabs/stable-diffusion-image-variations 6 months ago

Delete unsafe.png
#33 opened 6 months ago by Juno360219
New activity in nsfwDemo/551515 6 months ago

Create README.md
#1 opened 6 months ago by Juno360219
New activity in runwayml/stable-diffusion-v1-5 7 months ago

Update scheduler/scheduler_config.json
#186 opened 7 months ago by Juno360219

Delete
#185 opened 7 months ago by Juno360219

Delete safety_checker
#184 opened 7 months ago by Juno360219
New activity in stabilityai/stable-diffusion 7 months ago

new file
#18278 opened 7 months ago by Juno360219

hhh
#18279 opened 7 months ago by Juno360219
New activity in ckpt/counterfeit-xl 7 months ago

Create README.md
#2 opened 7 months ago by Juno360219
New activity in Deci/DeciDiffusion-v1-0 8 months ago

yes
#4 opened 8 months ago by Juno360219
New activity in Deci/DeciDiffusion-v1-0 8 months ago

re9lace
#1 opened 8 months ago by Juno360219
New activity in sahil2801/replit-code-instruct-glaive 10 months ago

!git clone https://github.com/CompVis/stable-diffusion.git
#4 opened 10 months ago by Juno360219
New activity in stabilityai/stable-diffusion 10 months ago

replace
#17372 opened 10 months ago by Juno360219
New activity in Shriharsh/Text_To_Image 10 months ago

cat
#1 opened 10 months ago by Juno360219
New activity in DeepFloyd/IF 10 months ago

Create nsfw

2
#354 opened 12 months ago by Juno360219
New activity in huggingface/Model_Cards_Writing_Tool 10 months ago

Upload unstable_model_card.md
#5 opened 10 months ago by Juno360219
New activity in CompVis/stable-diffusion-v1-4 11 months ago

# Stable Diffusion v1 Model Card This model card focuses on the model associated with the Stable Diffusion model, available [here](https://github.com/CompVis/stable-diffusion). ## Model Details - **Developed by:** Robin Rombach, Patrick Esser - **Model type:** Diffusion-based text-to-image generation model - **Language(s):** English - **License:** [Proprietary](LICENSE) - **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](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([CLIP ViT-L/14](https://arxiv.org/abs/2103.00020)) as suggested in the [Imagen paper](https://arxiv.org/abs/2205.11487). - **Resources for more information:** [GitHub Repository](https://github.com/CompVis/stable-diffusion), [Paper](https://arxiv.org/abs/2112.10752). - **Cite as:** @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } # 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 primarily trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), which consists of images that are 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. Stable Diffusion v1 mirrors and exacerbates biases to such a degree that viewer discretion must be advised irrespective of the input or its intent. ## Training **Training Data** The model developers used the following dataset for training the model: - LAION-5B and subsets thereof (see next section) **Training Procedure** Stable Diffusion v1 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 the following checkpoints: - `sd-v1-1.ckpt`: 237k steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en). 194k steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`). - `sd-v1-2.ckpt`: Resumed from `sd-v1-1.ckpt`. 515k steps at resolution `512x512` on [laion-aesthetics v2 5+](https://laion.ai/blog/laion-aesthetics/) (a subset of laion2B-en with estimated aesthetics score `> 5.0`, and additionally filtered to images with an original size `>= 512x512`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the [LAION-5B](https://laion.ai/blog/laion-5b/) metadata, the aesthetics score is estimated using the [LAION-Aesthetics Predictor V2](https://github.com/christophschuhmann/improved-aesthetic-predictor)). - `sd-v1-3.ckpt`: Resumed from `sd-v1-2.ckpt`. 195k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598). - `sd-v1-4.ckpt`: Resumed from `sd-v1-2.ckpt`. 225k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598). - **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](assets/v1-variants-scores.jpg) Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores. ## Environmental Impact **Stable Diffusion v1** **Estimated Emissions** Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact. - **Hardware Type:** A100 PCIe 40GB - **Hours used:** 150000 - **Cloud Provider:** AWS - **Compute Region:** US-east - **Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid):** 11250 kg CO2 eq. ## Citation @InProceedings{Rombach_2022_CVPR, author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn}, title = {High-Resolution Image Synthesis With Latent Diffusion Models}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {10684-10695} } *This model card was written by: Robin Rombach and Patrick Esser and is based on the [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).*
#221 opened 11 months ago by Juno360219

delete
#220 opened 11 months ago by Juno360219

delete

1
#219 opened 11 months ago by Juno360219

replace
#218 opened 11 months ago by Juno360219
New activity in stabilityai/stable-diffusion 11 months ago

replace
#16809 opened 11 months ago by Juno360219

Delete app.py
#16808 opened 11 months ago by Juno360219

Delete app.py
#16807 opened 11 months ago by Juno360219

replace
#16794 opened 11 months ago by Juno360219

replace
#16793 opened 11 months ago by Juno360219

Update app.py
#16792 opened 11 months ago by Juno360219

Create vb
#16777 opened 11 months ago by Juno360219

change t
#16776 opened 11 months ago by Juno360219

change th
#16775 opened 11 months ago by Juno360219

replace
#16774 opened 11 months ago by Juno360219

crested nsfw
#16764 opened 11 months ago by Juno360219

https://github.com/chemistzombie/stable-diffusion-unfiltered.git
#16757 opened 11 months ago by Juno360219
New activity in songweig/rich-text-to-image 11 months ago

gg
#18 opened 11 months ago by Juno360219
New activity in hakurei/waifu-diffusion 11 months ago

g

2
#131 opened 11 months ago by Juno360219
New activity in CompVis/stable-diffusion-v1-4 11 months ago

fg
#213 opened 11 months ago by Juno360219

fg
#212 opened 11 months ago by Juno360219
New activity in DeepFloyd/IF 12 months ago

nsfw
#353 opened 12 months ago by Juno360219

nee
#352 opened 12 months ago by Juno360219
New activity in stabilityai/stable-diffusion-2-1 12 months ago

Create g
#63 opened 12 months ago by Juno360219
New activity in runwayml/stable-diffusion-v1-5 12 months ago

Create common_google_play_services_enable_text
#136 opened 12 months ago by Juno360219
New activity in huseinzol05/text-to-speech-e2e-fastspeech-osman 12 months ago

Create README.md
#1 opened 12 months ago by Juno360219
New activity in JustinLin610/ImageBind_zeroshot_demo 12 months ago

fgg
#7 opened 12 months ago by Juno360219

Delete CODE_OF_CONDUCT.md
#6 opened 12 months ago by Juno360219
New activity in stabilityai/stable-diffusion 12 months ago

gg
#16125 opened 12 months ago by Juno360219

66
#16122 opened 12 months ago by Juno360219

delete.gitattributes
#16057 opened 12 months ago by Juno360219

Delete .gitattributes
#16056 opened 12 months ago by Juno360219

vv
#16055 opened 12 months ago by Juno360219

ggg
#16054 opened 12 months ago by Juno360219

Create yes
#16053 opened 12 months ago by Juno360219
New activity in unvailai/3DKX_1.0b 12 months ago

v vb
#3 opened 12 months ago by Juno360219

nnnn
#4 opened 12 months ago by Juno360219
New activity in multimodalart/latentdiffusion 12 months ago

no
#18 opened 12 months ago by Juno360219
New activity in vinthony/SadTalker 12 months ago

De

1
#4 opened 12 months ago by Juno360219
New activity in Zhenhong/text-to-image-Stable-Diffusion-demo 12 months ago

Yes
#2 opened 12 months ago by Juno360219

Bbhh
#1 opened 12 months ago by Juno360219