compvis/stable-diffusion issues and pull requests

#883 - Stable diffusion for unconditional generation?

Issue - State: open - Opened by rozyangno 24 days ago

#882 - Saksham

Issue - State: open - Opened by brij2140saksham about 1 month ago - 2 comments

#881 - ```suggestion

Issue - State: open - Opened by mamalieaz about 1 month ago

#879 - Create Stable-diffusion 1

Pull Request - State: open - Opened by Rmattmann501 2 months ago

#878 - Create Να

Pull Request - State: open - Opened by Giorgos008 2 months ago

#877 - Whats the difference between https://github.com/CompVis/stable-diffusion and https://github.com/CompVis/latent-diffusion

Issue - State: open - Opened by bhosalems 2 months ago - 5 comments

#876 - Confused with nll_loss

Issue - State: open - Opened by haichao2023 3 months ago - 2 comments

#875 - High quality, god quality

Issue - State: open - Opened by Sunflower344 3 months ago - 4 comments

#874 - AI img

Issue - State: open - Opened by RafiOrno 3 months ago

#873 - Why occurs Never Gonna Give You Up?????

Issue - State: closed - Opened by xiao10ma 4 months ago - 2 comments

#872 - Update?

Issue - State: open - Opened by IkibiSction 4 months ago

#871 - Have you solved this problem? I also want to know how this FID is calculated and how to reproduce it.

Issue - State: open - Opened by sir-zengqi 5 months ago - 1 comment

#870 - 想学习【文生图】快加学习交流群

Issue - State: open - Opened by km1994 5 months ago

#869 - Anime

Issue - State: open - Opened by NagatoKaiNi 6 months ago

#868 - I can't log in

Issue - State: open - Opened by JustAKidThatLikesCoding 6 months ago

#867 - Can`t launch the install.py

Issue - State: open - Opened by KnuckleDustes 7 months ago

#866 - Yyyy

Issue - State: open - Opened by Gerdek181 7 months ago

#865 - ModuleNotFoundError: No module named 'ldm.util'; 'ldm' is not a package . at img2img.py

Issue - State: open - Opened by nguyentri-art 7 months ago

#864 - ModuleNotFoundError: No module named 'imwatermark'

Issue - State: open - Opened by ctrlaltdelete31 7 months ago

#863 - Using Custom Picture Dataset in Stable Diffusion

Issue - State: open - Opened by nathan215 7 months ago

#862 - consuming food pouches by sucking.

Issue - State: open - Opened by shani-design 7 months ago

#861 - Example from homepage returns KeyError 'sample'

Issue - State: closed - Opened by HuangLED 8 months ago

#860 - OverflowError: cannot fit 'int' into an index-sized integer

Issue - State: open - Opened by zws98 8 months ago - 4 comments

#859 - Why bias in Q, K, V projection of SpatialSelfAttention?

Issue - State: open - Opened by SimeonZhang 8 months ago

#857 - CheckpointFunction: AttributeError: 'NoneType' object has no attribute 'detach'

Issue - State: closed - Opened by sivannavis 8 months ago - 3 comments

#856 - Galatasaray

Issue - State: open - Opened by Cbrlgmbr 8 months ago

#855 - 这是什么错误？应该如何解决啊？

Issue - State: open - Opened by 1030zero 9 months ago - 1 comment

#854 - mian.py

Issue - State: open - Opened by kkkkuka 9 months ago

#853 - Default config-checkpoint mapping for released models

Issue - State: open - Opened by silky1708 9 months ago

#852 - New

Issue - State: open - Opened by RempeKira 9 months ago

#851 - Fixes in ddpm.py and main.py

Pull Request - State: open - Opened by silky1708 9 months ago

#850 - UserWarning: 1Torch was not compiled with flash attention.

Issue - State: closed - Opened by stromyu520 9 months ago - 2 comments

#849 - Question about the KL divergence loss

Issue - State: open - Opened by marctimjen 10 months ago - 2 comments

#848 - discord control?

Issue - State: open - Opened by surgetheurge 10 months ago - 1 comment

#847 - Where can I get the one good with 256x256

Issue - State: open - Opened by Pang-0093 10 months ago - 1 comment

#846 - python scripts/txt2img.py --prompt "a cat" --plms

Issue - State: open - Opened by Gin3601 10 months ago - 3 comments

#845 - Calculation of timesteps for img2img tasks.

Issue - State: open - Opened by okaris 10 months ago

#844 - Create Gaussing_Diffusion.py

Pull Request - State: closed - Opened by Esmail-ibraheem 10 months ago

#843 - 翻译部分readme

Pull Request - State: closed - Opened by WZMIAOMIAO 11 months ago

#842 - How to use it with CPU?

Issue - State: open - Opened by KosmasF 11 months ago - 1 comment

#841 - RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 1 but got size 2 for tensor number 1 in the list.

Issue - State: open - Opened by atbgams 11 months ago - 2 comments

#840 - run 'python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms ' fail

Issue - State: open - Opened by Ellenke 11 months ago - 3 comments

#839 - the img2img scripts can't work

Issue - State: open - Opened by haye123 11 months ago

#838 - omegaconf.errors.ConfigAttributeError: Missing key data

Issue - State: open - Opened by parkjjoe 11 months ago - 2 comments

#837 - The separation of LoRa into separate folders has disappeared

Issue - State: open - Opened by amegared666 11 months ago

#836 - Multiple API Response from SDXL Model

Issue - State: open - Opened by Anbu-Divum 12 months ago

#835 - New Issue added for test

Issue - State: open - Opened by PriyankaPandhare 12 months ago - 6 comments

#832 - where is the classifier free guidance code

Issue - State: open - Opened by subhashnerella about 1 year ago - 1 comment

#829 - 10.5.0

Pull Request - State: open - Opened by arcanite24 about 1 year ago

#816 - Some weird problems: requests.exceptions.ProxyError: HTTPSConnectionPool(host='huggingface.co', port=443):

Issue - State: open - Opened by zhaosheng-thu about 1 year ago - 5 comments

#807 - Safetensor models

Issue - State: open - Opened by DaCosySheeep over 1 year ago - 1 comment

#796 - about the classifier-free guidance sampling code ?

Issue - State: open - Opened by JaosonMa over 1 year ago - 7 comments

#795 - Free Stable Diffusion API?

Issue - State: open - Opened by incomingflyingbrick over 1 year ago - 53 comments

#787 - Train my own stable diffusion model or fine-tune the base model

Issue - State: open - Opened by charlesyuJY over 1 year ago - 2 comments

#784 - freezing some blocks in UNet, and has RuntimeError: One of the differentiated Tensors does not require grad error

Issue - State: closed - Opened by lingtengqiu over 1 year ago - 8 comments

#781 - Torch 2.0.1 is not found, python version 3.10.6 installed how to fix this issue

Issue - State: open - Opened by Jusi468899 over 1 year ago - 1 comment

#775 - cannot import name 'CLIPTextModelWithProjection' from 'transformers'

Issue - State: open - Opened by LeoStrange26 over 1 year ago - 14 comments

#773 - Cannot Finetune the model after freezing some parameters in the Unet

Issue - State: open - Opened by alphacoder01 over 1 year ago - 4 comments

#768 - How to train ldm on a low-resolution image dataset (128*128)

Issue - State: open - Opened by crowningwang over 1 year ago - 1 comment

#766 - Autoencoder training details

Issue - State: open - Opened by jh27kim over 1 year ago - 3 comments

#759 - _pickle.UnpicklingError: invalid load key, 'm'.

Issue - State: closed - Opened by sussyboiiii over 1 year ago - 3 comments

#750 - OSError: Can't load config for 'CompVis/stable-diffusion-safety-checker'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'CompVis/stable-diffusion-safety-checker' is the correct path to a directory containing a config.json file

Issue - State: open - Opened by LKJ-np over 1 year ago - 6 comments

#735 - Only noise when training from scratch on COCO dataset

Issue - State: closed - Opened by alphacoder01 over 1 year ago - 6 comments

#734 - How to run it from a .BAT file

Issue - State: closed - Opened by pdavis68 over 1 year ago - 1 comment

#703 - TypeError: list indices must be integers or slices, not str

Issue - State: open - Opened by PhdShi almost 2 years ago - 1 comment

#697 - ImportError: cannot import name 'custom_collate' from 'taming.data.utils'

Issue - State: open - Opened by RuifengLu almost 2 years ago - 1 comment

#693 - how to train model?

Issue - State: open - Opened by woonwoon almost 2 years ago - 7 comments

#626 - [Question] how to fine-tune the Stable Diffusion Upscaler X4?

Issue - State: open - Opened by Estrellama almost 2 years ago - 4 comments

#597 - No module named 'ldm.util'; 'ldm' is not a package

Issue - State: open - Opened by Giaagaa about 2 years ago - 5 comments

#583 - How to compute the FID of text-image models?

Issue - State: open - Opened by jsttlgdkycy about 2 years ago - 1 comment

#562 - How to finetune inpainting model for object removal? What is the input prompt for object removal for both training and inference?

Issue - State: open - Opened by hdjsjyl about 2 years ago - 2 comments

#550 - Issues installing requirements via webui-user.bat

Issue - State: closed - Opened by hristo-naydenov about 2 years ago - 4 comments

#537 - The old url has changed.

Issue - State: open - Opened by RedlineBUPT about 2 years ago - 2 comments

#499 - Slable Diffusion - Imagem gerada preta

Issue - State: open - Opened by Yullki about 2 years ago - 1 comment

#465 - stochastic_encode

Issue - State: open - Opened by cloor over 2 years ago - 1 comment

#464 - FID-CLIP curve

Issue - State: open - Opened by amandaluof over 2 years ago - 5 comments

#425 - How can I finetune the VAE of stable diffusion?

Issue - State: closed - Opened by eeyrw over 2 years ago - 6 comments

#424 - OSError: All ports from 7860 to 7959 are in use. Please close a port

Issue - State: open - Opened by fatdennis over 2 years ago - 11 comments

#422 - How to finetune inpainting on custom dataset？

Issue - State: open - Opened by universewill over 2 years ago - 10 comments

#421 - FID/IS: how can i calculate the conditional models' FID/IS score?

Issue - State: open - Opened by zyx1213271098 over 2 years ago - 5 comments

#412 - Error reported running img2img.py

Issue - State: open - Opened by QQQTAO over 2 years ago - 2 comments

#411 - Different img2img results from DreamStudio

Issue - State: closed - Opened by iutlu over 2 years ago - 2 comments

#409 - Autoencoder training details

Issue - State: open - Opened by gombru over 2 years ago - 2 comments

#395 - KeyError: "filename 'storages' not found"

Issue - State: closed - Opened by VIXNESS over 2 years ago - 3 comments

#394 - OSError: Error no file named model_index.json found in directory

Issue - State: closed - Opened by DjTecmo over 2 years ago - 19 comments

#380 - Loss Logvar Scaling

Issue - State: open - Opened by jtawade over 2 years ago - 2 comments

#343 - correct configuration for sd-v1-4.ckpt

Issue - State: open - Opened by alemNative over 2 years ago - 3 comments

#336 - Can pretrained autoencoder stage be used for any new dataset training?

Issue - State: open - Opened by Revist over 2 years ago - 2 comments

#333 - Evaluation issuse

Issue - State: open - Opened by NieShenRuc over 2 years ago - 1 comment

#332 - Module Not Found Error imwatermark

Issue - State: open - Opened by SkimZconceited over 2 years ago - 8 comments

#314 - Why `make_beta_schedule` does not return linear schedule?

Issue - State: open - Opened by yutoe05 over 2 years ago - 4 comments

#309 - Failure creating conda env on OSX amd64 - ResolvePackageNotFound: cudatoolkit=11.3

Issue - State: open - Opened by ivandov over 2 years ago - 29 comments

#305 - What is 10% dropping of the text-conditioning?

Issue - State: open - Opened by luffycodes over 2 years ago - 3 comments

#304 - Transparent backgrounds for output instead of black color for sprites generation (Is that possible?)

Issue - State: open - Opened by toasterhead-master over 2 years ago - 12 comments

#302 - OSError: CompVis/stable-diffusion-v1-4 does not appear to have a file named config.json.

Issue - State: open - Opened by XavierXiao over 2 years ago - 18 comments

GitHub / compvis/stable-diffusion issues and pull requests