Request DOI:
#257 opened 8 days ago
by
squaabee
Request: DOI
#256 opened 13 days ago
by
Gasedak2
ValueError: too many values to unpack (expected 2)
#255 opened about 2 months ago
by
ChaseXuu
Add generated example
#254 opened 2 months ago
by
promesn
Request: DOI
#253 opened 2 months ago
by
deleted
Upload config.json
#252 opened 3 months ago
by
alirizvipk
Add generated example
#251 opened 3 months ago
by
Spintron
How to Download Main?
1
#249 opened 5 months ago
by
FlagrantYeti
pip uninstall opencv-python
#248 opened 6 months ago
by
Bertjer
Request: DOI
#247 opened 6 months ago
by
Asan2
Request: DOI
#246 opened 6 months ago
by
noakrispin
Request: DOI
1
#245 opened 8 months ago
by
ImArchimedes
Update performance link
#244 opened 8 months ago
by
ZennyKenny
Request: DOI
#243 opened 8 months ago
by
awdfawaw
I am new to developement i want to know where to find vae_decoder.ckpt
1
#242 opened 9 months ago
by
AnilMnr
how to train train new model with different channel number in unet
#241 opened 10 months ago
by
jonathan0227
Adding `safetensors` variant of this model
#240 opened about 1 year ago
by
LIqipei
Adding `safetensors` variant of this model
#239 opened about 1 year ago
by
LIqipei
OSError: CompVis/stable-diffusion-v1-4 does not appear to have a file named config.json. Checkout 'https://huggingface.co./CompVis/stable-diffusion-v1-4/None' for available files.
8
#238 opened about 1 year ago
by
Lily0512
OSError: /CompVis/stable-diffusion-v1-4/ does not appear to have a file named config.json.
9
#237 opened about 1 year ago
by
Kayell
RuntimeError
#236 opened about 1 year ago
by
kangxi1818
AttributeError: 'AutoencoderKLOutput' object has no attribute 'sample'
#235 opened about 1 year ago
by
Nobparad
Update README.md
#232 opened over 1 year ago
by
Cheet0s
Is this normal?
#229 opened over 1 year ago
by
DadOfWinter
Femdom
3
#228 opened over 1 year ago
by
Wowa23478fak
Femdom
#227 opened over 1 year ago
by
Wowa23478fak
Upload stable-diffusion-v1-4.ckpt
#224 opened over 1 year ago
by
hipsterweeds
where to download the "sd-v1-4.ckpt" it's not in the "files and versions" where did it go??
3
#223 opened over 1 year ago
by
StarektTheDEv
Train an unconditional LDM on different classes, is it ok?
#222 opened over 1 year ago
by
Vincent171
# 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 over 1 year ago
by
Juno360219
RuntimeError: CUDA out of memory in stable diffusion
2
#217 opened over 1 year ago
by
Ahmed960
Connection refused on localhost (127.0.0.1:7860)
1
#215 opened over 1 year ago
by
fubidou
How to set optional parameters? How to set the size of an image?
#214 opened over 1 year ago
by
blansj
fg
#213 opened over 1 year ago
by
Juno360219
fg
#212 opened over 1 year ago
by
Juno360219
Update README.md
#210 opened over 1 year ago
by
MrRobotoAI
How to set negative prompt in pipe?
3
#208 opened over 1 year ago
by
renshengchangzui
Create .ckpt
#207 opened over 1 year ago
by
aye14223
RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half'
3
#206 opened over 1 year ago
by
jin941013
If you don't know how to download it
#204 opened over 1 year ago
by
Hektop
Select and Load Model Error
#202 opened almost 2 years ago
by
avigra
🚩 Report
#201 opened almost 2 years ago
by
141ADAKDHIH
Create ada
#200 opened almost 2 years ago
by
Valkig
RuntimeError
1
#199 opened almost 2 years ago
by
thomaszaap
Error: got an unexpected keyword argument 'init_image'
1
#198 opened almost 2 years ago
by
zennee
розовый фон
#197 opened almost 2 years ago
by
darpax
🚩 Report : Ethical issue(s)
#195 opened almost 2 years ago
by
ziyuh
error in colab while running from diffusers import StableDiffusionPipeline
#191 opened almost 2 years ago
by
supriyo