Home
Creators
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register Favorites Keys Review DMs Logout
Community
Telegram ThePornDude
Home Creators Posts Import Register Favorites Logout

1 Click Automatic Installer & A Very Advanced GUI For InstantId For Windows, RunPod, Linux & Kaggle Notebook (Patreon)

Published:
2024-06-21 01:00:00
Edited:
2024-12-22 16:39:07
Imported:
2026-06

Downloads

Content

This post is now only history and obsolete

new post : https://www.patreon.com/posts/118469722

This post is now only history and obsolete

new post : https://www.patreon.com/posts/118469722

This post is now only history and obsolete

new post : https://www.patreon.com/posts/118469722

Join discord and tell me your discord username to get a special rank : SECourses Discord

How to use NGROK to connect Gradio apps on free Kaggle notebooks : https://youtu.be/iBT6rhH0Fjs

16 August 2024 Update:

InstantID updated to V22

Test all LoRA combinations added that you can test every model + every LoRA combination

LoRA scale was not working properly when you change them - this issue fixed

LoRA loading and unloading was not working properly - this issue fixed

Reloading pipe in each case fixed - now only LoRA weights loaded and unloaded

Way more accurately and faster working than before

New Pro Headshot preset added

Diffusers version upgraded to 0.30.0 so you should windows update and call install bat file again or manually upgrade diffusers ver

3 July 2024 Update V14:

Zip file updated to : instant_id_v19.zip

New feature Change applied LoRA Scale added under LoRA selection section

You can now set the applied power / strength / scale of LoRAs

Just run Windows_Update_Version.bat if you had Version 13

Libraries updated to latest versions

Per step speed added to the command line interface window (CMD - Terminal)

Kaggle notebook updated to V4 - now uses kaggle/temp directory so we can download more models

A cell added to the Kaggle notebook to download SDXL Base 1.0, RealVisXL 4.0, Juggernaut_XL_v9 and Juggernaut_XL_v10 into models folder automatically

30 April 2024 Update V13:

InstantID updated to V13

FP4 and FP8 support added. Thus even with 8 GB GPUs now you can use amazingly

Fully supporting older weak GPUs as well

Kaggle notebook updated and now works much better than before with FP8

Kaggle notebook is inside the zip file

Massed Compute installers and instructions added to the zip file

RunPod installers and instructions added to the zip file

Newest lower precision and cpu offloading required VRAMs as below

Several metadata saving and loading bugs fixed. E.g. it was saving style prompts as well or was giving error when you didn't use any

18 March 2024 Update V12:

InstantID updated to V12

Now Metadata of the images will be saved into saved images

You can load and see Metadata from newly added Image Metadata tab

Load & Set Metadata Settings buttons will load and set the same settings of particular generated image including input images

If images are not existing anymore they won't be set

update_windows_version .bat file will update to this version if you have V11

If still doesn't work try to run update_windows_requirements .bat

If still not work install into a new folder like C:/instant_id_v13

25 February 2024 Update V11: 

LoRA model support added

You can even use multiple LoRAs at the same time 

Select the LoRA models from LoRA model dropdown 

The Gradio will scan loras folder inside the InstantID folder

You can also give custom LoRA models folder path with this argument --loras_path 

Example full argument 

python gradio_demo\web-ui-multicontrolnet.py %extra_args% --models_path "G:\automatic1111\stable-diffusion-webui\models\Stable-diffusion" --loras_path "G:\automatic1111\stable-diffusion-webui\models\Lora"

Download latest InstantID and extract into folder where you want to install

LCM sampler bug fixed but it is really bad quality

Installer library version bug fixed

App screenshot updated : instant id app screenshot.png

21 February 2024 Update:

Face cropping feature massively improved to support

Different aspect ratio having input face

Different aspect ratio having outputs 

Please do a fresh install as we have a new library dependency 

Also the detected face and cropped input images will be saved inside temp_faces folder inside InstantID foder

We also did a fix to lowvram option which was causing 1 click working 1 click error 1 click working

Please report any other errors you might encounter 

20 February 2024 Massive Update:

Fixed model reloading with V5 update

New style and depth model added as well

In rare occasions CPU Offloading could cause error especially on Kaggle

This error is fixed

Added refresh models feature - Only SDXL models work

Fixed RunPod instructions error

If you want to use existing models folder: edit run_web_UI. bat and add your folder path as below  

--models_path "G:\automatic1111\stable-diffusion-webui\models\Stable-diffusion"

Don't forget "" and give your own model path

18 February 2024 Massive Update:

Now supports Pose, Canny & Depth ControlNets - all auto installed & downloaded

Single controlnet web app removed since all optimizations applied to multi controlnet and should work very well even with 8GB GPUs

When starting the app it will ask you Low VRAM option, Gradio Live share option and FP16 option

Use Low VRAM option if you have lesser than 16 GB GPUs

Low VRAM option will enable CPU offloading and it is super optimized. All thanks to amazing work of Pelolisu from our Discord channel

Use FP16 option if you have older GPUs such as RTX 1080 TI which doesn't support BF16

Use Gradio Live share if you want to share your app or if you are running it in RunPod or such cloud, etc

Kaggle notebook also updated to latest version

On Kaggle notebook, if you want to use ControlNets you need to add --lowvram to starting parameter

However this will slow down the generation a lot

Without additional ControlNets, Kaggle works super fast

RunPod instructions txt file added. Just change the paths if you are a Linux user

10 February 2024 Update:

Automatic image cropping feature added so now you can upload any aspect ratio image and get any aspect ratio output image - it is auto active

CPU offloading feature added to the single controlnet gradio app so it works super fast with 12GB / 10GB GPUs even 8GB gpus should work fine now just reduce target resolution

Multi-ControlNet app is also now supporting CPU offloading and with 16GB GPU you should be able to use it very fast with multiple ControlNet at the same time

To update either do a git pull or do a fresh install

How to do git pull : https://youtu.be/-NjNy7afOQ0

Full tutorial video : in production

Fully automatic installers for Windows and Linux for InstantID : Zero-shot Identity-Preserving Generation in Seconds > https://instantid.github.io/

Watch it to learn how to install Python (3.10), Visual C++ tools properly > https://youtu.be/-NjNy7afOQ0 since you need C++ tools installed for InsightFace library

Features

1 click install on Windows (local) and RunPod and Kaggle (free account) and Linux (local or cloud) systems

It will install everything and download everything into a new VENV

Advanved Gradio Web APP compared to the official demo with following features

xFormers - faster

Custom image resolutions - enter any final resolution of image you want (some specific resolutions may fail but common ones working like 768x1024, 1024x1280, 768x768, etc.)

Scans models folder and let you pick any model from there

Give full path or Hugging Face repo of any model with an input box

Generate any number of images like set 200 images and it will generate 200 image

Every image is saved by default into the outputs folder

I am talking with developers to add extra lower VRAM (probably below 6 GB) feature

Supports pose, canny & depth ControlNet combination

Comparisons & Experiments

CFG comparisons 4 vs 4.5 vs 5, 6, 7, 8, 9, 10 (I think 4 is best with our technique) :

https://imgsli.com/Mjc2ODcw/0/1

Schedulers comparison (I think DPMSolverMultistepScheduler-Karras is best) :

https://imgsli.com/Mjc2ODcy/0/4

IdentityNet strength comparisons (I feel like 0.6 is best with our technique)

https://imgsli.com/Mjc2ODc5/5/3

Image adapter strength comparisons (I feel like 1.0 is best with our technique )

https://imgsli.com/Mjc2ODg0/7/5

Tips

Select target resolution with same aspect ratio of your input image

Crop your input image with same aspect ratio of your desired output resolution

E.g. input image is 1746x2619 so target resolution can be 768x1152 - same aspect ratio 

I use resize feature of Paint .Net (free open source) to find target resolution or cropping 

You can download any SDXL model from CivitAI or Hugging Face and use. Download into models folder inside InstantID folder and restart the APP

Requirements

Tested on Python 3.10.11 so use Python 3.10.x

C++ tools has to be installed for InsightFace library

Full tutorial to install these 2 : https://youtu.be/-NjNy7afOQ0

Windows Install Instructions

Download instant_id . zip from attachments

Extract files into any folder you want to install

First double click windows_install .bat and install the InstantID

Kaggle Instructions

Upload kaggle notebook inside zip file (import notebook)

Select Python and GPT T4 x2 and Internet On

Instructions are well written on the Notebook

Files

Comments

Bartosz Polecki

Thanks Mate, everything is working great.

sebastien laroche

hello, thank you for your work. Maybe I'm bad, but I can't install models. I go to Civitai, download the chekpoints in the instantID "model" folder, but as soon as I want to use them I get errors. I'm on Runpod (usually on the 3090). my line of code for installation: wget *model address* -content-disposition. I've also tried the hugginface repo, but I don't know where to find the right links. Thanks in advance for enlightening the blind man that I must be ;)

sebastien laroche

Thank you very much, it works! I had to rename the files by deleting a large part of the file name. One model didn't work (UTF-8 encoding problem apparently), but that's not too serious :) One last question: Where can I find the right link for the hugginface repo? Thanks again :)

Pallavi Chauhan

wouldn't be easier if we download all the models just once in our pc and use runpodctl to transfer those on runpod? I haven't tried that yet so can't compare the download speed with 8-10 models ,using runpodctl and manual upload of hugging face. But I definitely know the slow speed from civitai and the link we use with browser cookies does expire the next day or so then we need a new link so that's not good at all.

sebastien laroche

Hello, I've just tested V2 but, unless I've made a mistake somewhere, there's a problem. Each time an image is generated, it reloads the model I'm using, which makes each image generation very long. It didn't do that with the previous version.

sebastien laroche

"Unfortunately" i'm on a Mac and use Runpod for my generations. Anyway, thanks for always updating your scripts regularly, it's a great job!

sebastien laroche

Thank you very much, it works much faster. Thanks also for the speed and efficiency. I do not regret my modest participation.

Steve

RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select)

Steve

Low vram, no gradio share, and BF16. First image came out ok but I realized the watercolor option was on I turned it off and it stopped working. Closed and reopened it seems my first image always come out ok but subsequent images get the error.

Steve

Loading model: wangqixun/YamerMIX_v8 The config attributes {'controlnet_list': ['controlnet', 'RPMultiControlNetModel'], 'requires_aesthetics_score': False} were passed to StableDiffusionXLInstantIDPipeline, but are not expected and will be ignored. Please verify your model_index.json configuration file. Keyword arguments {'controlnet_list': ['controlnet', 'RPMultiControlNetModel'], 'requires_aesthetics_score': False, 'safety_checker': None} are not expected by StableDiffusionXLInstantIDPipeline and will be ignored. Model loaded successfully. Start inference... [Debug] Prompt: watercolor painting, full body photo, professional photo . vibrant, beautiful, painterly, detailed, textural, artistic, [Debug] Neg Prompt: (lowres, low quality, worst quality:1.2), (text:1.2), watermark, anime, photorealistic, 35mm film, deformed, glitch, low contrast, noisy (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, monochrome Image 1/1 generated in 28.55 seconds. 1 images generated in 28.55 seconds, average 28.55 seconds per image. input image cropped according to target width and height W:\InstantID\InstantID\venv\lib\site-packages\insightface\utils\transform.py:68: FutureWarning: `rcond` parameter will change to the default of machine precision times ``max(M, N)`` where M and N are the input matrix dimensions. To use the future default and silence this warning we advise to pass `rcond=None`, to keep using the old, explicitly pass `rcond=-1`. P = np.linalg.lstsq(X_homo, Y)[0].T # Affine matrix. 3 x 4 No model selected or inputted. Default model will be used. Model loaded successfully. Start inference.. [Debug] Prompt: full body photo, professional photo, [Debug] Neg Prompt: (text:1.2), watermark, (frame:1.2), deformed, ugly, deformed eyes, blur, out of focus, blurry, monochrome Traceback (most recent call last): File "W:\InstantID\InstantID\venv\lib\site-packages\gradio\queueing.py", line 495, in call_prediction output = await route_utils.call_process_api( File "W:\InstantID\InstantID\venv\lib\site-packages\gradio\route_utils.py", line 233, in call_process_api output = await app.get_blocks().process_api( File "W:\InstantID\InstantID\venv\lib\site-packages\gradio\blocks.py", line 1608, in process_api result = await self.call_function( File "W:\InstantID\InstantID\venv\lib\site-packages\gradio\blocks.py", line 1176, in call_function prediction = await anyio.to_thread.run_sync( File "W:\InstantID\InstantID\venv\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "W:\InstantID\InstantID\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 2144, in run_sync_in_worker_thread return await future File "W:\InstantID\InstantID\venv\lib\site-packages\anyio\_backends\_asyncio.py", line 851, in run result = context.run(func, *args) File "W:\InstantID\InstantID\venv\lib\site-packages\gradio\utils.py", line 689, in wrapper response = f(*args, **kwargs) File "W:\InstantID\InstantID\venv\lib\site-packages\gradio\utils.py", line 689, in wrapper response = f(*args, **kwargs) File "W:\InstantID\InstantID\gradio_demo\web-ui-multicontrolnet.py", line 503, in generate_image result_images = pipe( File "W:\InstantID\InstantID\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "W:\InstantID\InstantID\.\pipelines\pipeline_stable_diffusion_xl_instantid_full.py", line 910, in __call__ ) = lpw.get_weighted_text_embeddings_sdxl( File "W:\InstantID\InstantID\.\pipelines\pipeline_stable_diffusion_xl_instantid_full.py", line 426, in get_weighted_text_embeddings_sdxl prompt_embeds_1 = pipe.text_encoder(token_tensor.to(pipe.device), output_hidden_states=True) File "W:\InstantID\InstantID\venv\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "W:\InstantID\InstantID\venv\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "W:\InstantID\InstantID\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 798, in forward return self.text_model( File "W:\InstantID\InstantID\venv\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "W:\InstantID\InstantID\venv\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "W:\InstantID\InstantID\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 691, in forward hidden_states = self.embeddings(input_ids=input_ids, position_ids=position_ids) File "W:\InstantID\InstantID\venv\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "W:\InstantID\InstantID\venv\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "W:\InstantID\InstantID\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 216, in forward inputs_embeds = self.token_embedding(input_ids) File "W:\InstantID\InstantID\venv\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "W:\InstantID\InstantID\venv\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "W:\InstantID\InstantID\venv\lib\site-packages\torch\nn\modules\sparse.py", line 163, in forward return F.embedding( File "W:\InstantID\InstantID\venv\lib\site-packages\torch\nn\functional.py", line 2237, in embedding return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse) RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select)

Steve

I don't think it has to do with changing the style anymore, I think that was a coincidence. It seems everytime I load it the first picture comes out ok but all subsequent photos even with same settings produce that error.

Steve

I just installed InstantID now with the one click installer, Python 3.10.11, RTX 4070

Khoa Vo

How do I get this to use my existing A1111 model folder? Also I can't even find the existing model folder it's trying to load.

Dmitry

Hello, There were 2 problems(RunPod) 1) For some reason, when I select an aspect ratio that differs from 1:1, it gives an error. It doesn't matter which input image I upload, you can only create an error-free image with a 1:1 ratio. 2) After uploading the model to the InstantID/models folder, it did not appear in the pop-up list UPD Problem 1 has been solved. If the smaller of the sides in the output image is less than 800 pixels, then there will be an error PS In the instructions of the txt file to install on the RunPod, the slash “\” was in the wrong direction (python gradio_demo\web-ui-multicontrolnet.py --share), which is why the command was not executed. I am completely zero in understanding the code, what is the problem ChatGPT helped to solve, it may be worth fixing it in the instructions

Dmitry

The function is working, thanks a lot, the model has appeared. Can you tell me where I can add my styles, if possible? PS Errors occur with some parameters of the output image. When I set the ratio 800:1000, it gives an error, when I set the ratio 800:1024, the generation works. I'm trying to figure out what's going on

Erosi

Wherein the batch file? does it matter?

Khoa Vo

Have you tried photomaker? I wonder if it has better quality since you can put in more than one image as reference.

Mark Sutherland

I'm run v3 v6 and it's taking well over an hour to generate one image. No idea whats going on with it,

Mark Sutherland

Hi, Nvidia RTX A4000 16GB, yes using low vram option, how can I tell how much vram used before starting the app, cheers

Mark Sutherland

thanks for reply. I ran that cmd, running on windows, not sure if this has anything to do with it but in the cmd bos it says

Mark Sutherland

raise local protocol error too little data for declared content length likewise for h11._util.localprotocolError to little data for declared content-length

sebastien laroche

Hi, i've just tested version 9 on runpod A6000, following the instructions in the readme file, but unfortunately an "out of memory" error stopped me before I could generate an image. here's the problem : torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 12.00 MiB. GPU 0 has a total capacity of 47.54 GiB of which 10.00 MiB is free. Process 239789 has 47.52 GiB memory in use. Of the allocated memory 867.36 MiB is allocated by PyTorch, and 2.64 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)

Dmitry

Hello, is there a difference in the quality of generation in the local instantID and instant ID in automation 1111?

Dazzastrous

Please select an option for VRAM usage (default 1): 1. High VRAM (Faster) 2. Low VRAM (A Little Bit Slower) - Preffered For Cards Below 16GB VRAM Enter your choice (1-2): 1 -- Please select an option for Gradio Share (default 1): 1. Without Gradio Share 2. With Gradio Share Enter your choice (1-2): 1 -- Please select an option for Precision Type (default 1): 1. With BF16 (preffered better faster choice) 2. With FP16 (only useful for old GPUs such as RTX 1080 TI) Enter your choice (1-2): 1 -- 2024-02-21 13:07:54.080108: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. WARNING:tensorflow:From E:\INSTANT_ID_V9\InstantID\venv\lib\site-packages\keras\src\losses.py:2976: The name tf.losses.sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead. download_path: ./models\antelopev2 Downloading ./models\antelopev2.zip from https://github.com/deepinsight/insightface/releases/download/v0.7/antelopev2.zip... Traceback (most recent call last): File "E:\INSTANT_ID_V9\InstantID\gradio_demo\web-ui-multicontrolnet.py", line 78, in app = FaceAnalysis( File "E:\INSTANT_ID_V9\InstantID\venv\lib\site-packages\insightface\app\face_analysis.py", line 27, in __init__ self.model_dir = ensure_available('models', name, root=root) File "E:\INSTANT_ID_V9\InstantID\venv\lib\site-packages\insightface\utils\storage.py", line 28, in ensure_available return download(sub_dir, name, force=False, root=root) File "E:\INSTANT_ID_V9\InstantID\venv\lib\site-packages\insightface\utils\storage.py", line 17, in download download_file(model_url, File "E:\INSTANT_ID_V9\InstantID\venv\lib\site-packages\insightface\utils\download.py", line 73, in download_file raise RuntimeError("Failed downloading url %s" % url) RuntimeError: Failed downloading url https://github.com/deepinsight/insightface/releases/download/v0.7/antelopev2.zip Press any key to continue . . .

sebastien laroche

I've just tested the update and yes, everything is working properly again! great, thank you very much :)

Ec Jep

Thanks for catching the TE1 not working. I trained yesterday and didn't notice Koyha kept "text_encoder1: false" even though it had a rate. The training output was still amazing but am training again today with TE1 set to True so it will be a good comparison. BTW RealVisXL4 appears to be an improvement on realism

Hazem

Does it work only with SDXL checkpoints ? or 1.5 checkpoints also work ?

Hung Do

Can you upgrade the codes and add Loras? Please

Ec Jep

just finished TE training and honestly very close and I would choose the non TE over TE...

Hung Do

Am talking about "A Very Advanced GUI For InstantId" Gradio Demo this thread ! not training. Would be nice to use Loras. It would expand InstantID GUI to bigger possibility such as thousand of Loras on Civitai..

Hung Do

when was the last time someone tell you that you are awesome

Mark Sutherland

I get this error with v10 \AppData\Local\Programs\Python\Python310\python.exe: can't open file 'I:\\INSTA10 LORA\\gradio_demo\\web-ui-multicontrolnet.py': [Errno 2] No such file or directory Press any key to continue . . .

100Sachen80

When generating it gives an error about BF16. But only since v10. Can i download v9 or older anywhere?

100Sachen80

Will reinstall v10 (deleted it already) and give you info about the exakt error (I have a nvidia 3060 12GB)

Mark Sutherland

I get an error on installation and the same error as before just a different directory. \AppData\Local\Programs\Python\Python310\python.exe: can't open file 'C:\\downloader.py': [Errno 2] No such file or directory C:\\instant_id\\gradio_demo\\web-ui-multicontrolnet.py': [Errno 2] No such file or directory Press any key to continue . . .

Bartosz Polecki

Hi, im getting error with version 10: RuntimeError: "upsample_bilinear2d_out_frame" not implemented for 'BFloat16'

100Sachen80

v11 works now, thank you very much!

Rick B

Working great on Kaggle with notebook from 25 Feb. Using it with & without ControlNet (lowvram option). Thanks

So Sha

I was able to install it on my ubuntu OS. but when I click on submit button I get this error: ( I haven't install it in /workspace folder ) File "/usr/lib/python3.10/os.py", line 215, in makedirs makedirs(head, exist_ok=exist_ok) File "/usr/lib/python3.10/os.py", line 215, in makedirs makedirs(head, exist_ok=exist_ok) File "/usr/lib/python3.10/os.py", line 225, in makedirs mkdir(name, mode) PermissionError: [Errno 13] Permission denied: '/workspace'

SECourses: FLUX, Tutorials, Guides, Resources, Training, Scripts

hello. it means there is still 1 error you didn't fix path. you obviously don't have /workspace. in my code I have no such hard coded path since it works both on Windows and RunPod. check your installation again. you shouldnt have any path as workspace

So Sha

It would be great if you could provide instructions for local linux users as well. Whenever I change the path from /workspace to my path I get "No such file or directory" error!

Evan Helga

Hello I found error, and also I dont see anything at InstantID\models\ Downloading ./models/antelopev2.zip from https://github.com/deepinsight/insightface/releases/download/v0.7/antelopev2.zip... Traceback (most recent call last): File "/kaggle/working/InstantID/gradio_demo/web-ui-multicontrolnet.py", line 85, in app = FaceAnalysis( File "/opt/conda/lib/python3.10/site-packages/insightface/app/face_analysis.py", line 27, in __init__ self.model_dir = ensure_available('models', name, root=root) File "/opt/conda/lib/python3.10/site-packages/insightface/utils/storage.py", line 28, in ensure_available return download(sub_dir, name, force=False, root=root) File "/opt/conda/lib/python3.10/site-packages/insightface/utils/storage.py", line 17, in download download_file(model_url, File "/opt/conda/lib/python3.10/site-packages/insightface/utils/download.py", line 73, in download_file raise RuntimeError("Failed downloading url %s" % url) RuntimeError: Failed downloading url https://github.com/deepinsight/insightface/releases/download/v0.7/antelopev2.zip

Hung Do

I have a problem. This works so well (fun) with styles, loras, models that after few hours of playing with a different combination, I ended up with a folder of nearly 100 images. Among them, I found a few looks that I like. So here is the problem, I can't seem to be able to to repeat the look. Can I beg for embed metadata in the PNG or an adjacent text file with same file name that show the configuration? At least which Lora(s) and Checkpoint I used. If someone come up with a different solution to log the process I am all ears.

Hung Do

Idealy, in metadata of the PNG, less messy to deal with. It could go into the comment section of PNG metadata which can be view with free software XnView. text files would work. it will be better than being blind. I would save them next to the image with the same file name in the output folder. Similar to the text description for each image in training. We are used to that

Evan Helga

Last time I try at kaggle. I get error File "/opt/conda/lib/python3.10/tempfile.py", line 483, in func_wrapper return func(*args, **kwargs) OSError: [Errno 28] No space left on device

Evan Helga

I try with the fresh one, how to use kaggle temp?

Stephen Yip

Installed InstantID v12 on Kaggle using the Installer. Images seems generated but not viewable in Webui. Runtime Error: no "view" mailcap rules found for type "application/octet-stream". For your kind advise Dr, Thank you! -------------------- Image 1/1 generated in 70.76 seconds. 1 images generated in 70.76 seconds, average 70.76 seconds per image. Warning: unknown mime-type for "/kaggle/working/InstantID/outputs" -- using "application/octet-stream" Error: no "view" mailcap rules found for type "application/octet-stream" /usr/bin/xdg-open: 869: www-browser: not found /usr/bin/xdg-open: 869: links2: not found /usr/bin/xdg-open: 869: elinks: not found /usr/bin/xdg-open: 869: links: not found /usr/bin/xdg-open: 869: lynx: not found /usr/bin/xdg-open: 869: w3m: not found xdg-open: no method available for opening '/kaggle/working/InstantID/outputs'

Stefan K

This will not work with an AMD gpu correct?

Stefan K

I see, thank you, as it asks for nvidia graphics card drivers, it might not work :(

Steve

fresh install of v13: Traceback (most recent call last): File "W:\InstantIDmostnewest\InstantID\gradio_demo\web-ui-multicontrolnet.py", line 29, in from pipelines.pipeline_common import quantize_4bit File "W:\InstantIDmostnewest\InstantID\.\pipelines\pipeline_common.py", line 4, in import bitsandbytes as bnb ModuleNotFoundError: No module named 'bitsandbytes'

Steve

tried running update requirements as well as update version, deleted venv reinstalled same error.

Steve

New file is good. I like what you did with the minimum requirements and the option#s makes it very easy to select the best choice

鸣 陈

I have a few questions 1. Where should the large model be placed? I did not find the location of the large model. 2. You can add an IPAdapter_plus. I upload a picture and you can directly refer to it to learn his style.

鸣 陈

Do you mean the current one is better? I would like to ask, how can I let him refer to my style?

鸣 陈

I only saw uploaded pictures of faces and movements, but no reference to my own style.

鸣 陈

I may not have expressed my thoughts correctly I see you made a Style template. I have my own Style template. What should I do?

zhou jie

can we use insitantid with inpainting?

Lou

Have you seen Krita AI? I just discovered it today. It's an open source ai plug in for Krita (a free open source photoshop type program). From the github description "Streamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required." It's an amazing plug in which allows real time inpainting, lora and base model support...SD or XL. ComfyUI back end. Super easy to install and use. Very robust and user friendly. It might be worth a look for a future tutorial video. https://github.com/Acly/krita-ai-diffusion

Algi

How much space does this all take? Accidetaly filled my HD first atempt to install.. would be good to write out so people know =)

Scott

I agree, that krita plug-in is amazing for doing in-painting, especially. It's so much nicer to have a decent graphics program with layers. It puts just the in-painted stuff on it's own layer where you can erase parts you don't want or move and re-align or other stuff. Automatic 1111 sucks for doing in-painting in comparison . The live in-painting I think is just a lightning model or a LoRA or something that makes the checkpoint generate like lightning. I tried a gimp plugin which was pretty basic and used automatic 1111 as the backend, but I can't stand gimp since it's such a UX dumpster fire, the UI is ugly and every simple manipulation take twice the steps necessary. There's one for Photoshop too, but I'm not going to rent their software from them. Time to dump Adobe.

ProulxMila (edited)

Comment edits

2026-09-07 10:00 16 August 2024 Update: InstantID updated to V22 but there's download only for instant_id_v19.zip
2024-09-23 14:15

Huey

I installed v19 in windows 11 but got the following errors : Modify this file and add --share if you want Gradio share Options VRAM usages are as below. No controlnet or LoRA used so these are min requirements 1+1 = 13 GB, 1+2 = 10 GB , 1+3 = 8.5 GB, 2+1 = 10.5 GB, 2+2 = 8.2 GB , 2+3 = 6.9 GB Please select an option: 1. Default - Faster but higher VRAM 2. Enable CPU Offloading - Reduces VRAM but changes output. I would avoid if possible Enter your choice (1-2): 1 Please select an option: 1. Default Precision (Half BF16-FP16) - Higher quality higher VRAM 2. FP8 Precision - Slightly lower quality medium VRAM 3. FP4 Precision - More slightly lower quality lower VRAM Enter your choice (1-3): 1 Traceback (most recent call last): File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\utils\import_utils.py", line 811, in _get_module return importlib.import_module("." + module_name, self.__name__) File "C:\Python310\lib\importlib\__init__.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "", line 1050, in _gcd_import File "", line 1027, in _find_and_load File "", line 1006, in _find_and_load_unlocked File "", line 688, in _load_unlocked File "", line 883, in exec_module File "", line 241, in _call_with_frames_removed File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\loaders\lora_pipeline.py", line 33, in from .lora_base import LoraBaseMixin File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\loaders\lora_base.py", line 47, in from peft.tuners.tuners_utils import BaseTunerLayer File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\peft\__init__.py", line 22, in from .auto import ( File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\peft\auto.py", line 32, in from .mapping import MODEL_TYPE_TO_PEFT_MODEL_MAPPING File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\peft\mapping.py", line 25, in from .mixed_model import PeftMixedModel File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\peft\mixed_model.py", line 29, in from .peft_model import PeftModel File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\peft\peft_model.py", line 37, in from transformers import Cache, DynamicCache, EncoderDecoderCache, PreTrainedModel ImportError: cannot import name 'EncoderDecoderCache' from 'transformers' (C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\transformers\__init__.py) The above exception was the direct cause of the following exception: Traceback (most recent call last): File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\utils\import_utils.py", line 811, in _get_module return importlib.import_module("." + module_name, self.__name__) File "C:\Python310\lib\importlib\__init__.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "", line 1050, in _gcd_import File "", line 1027, in _find_and_load File "", line 1006, in _find_and_load_unlocked File "", line 688, in _load_unlocked File "", line 883, in exec_module File "", line 241, in _call_with_frames_removed File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\pipeline_stable_diffusion.py", line 24, in from ...loaders import FromSingleFileMixin, IPAdapterMixin, StableDiffusionLoraLoaderMixin, TextualInversionLoaderMixin File "", line 1075, in _handle_fromlist File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\utils\import_utils.py", line 801, in __getattr__ module = self._get_module(self._class_to_module[name]) File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\utils\import_utils.py", line 813, in _get_module raise RuntimeError( RuntimeError: Failed to import diffusers.loaders.lora_pipeline because of the following error (look up to see its traceback): cannot import name 'EncoderDecoderCache' from 'transformers' (C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\transformers\__init__.py) The above exception was the direct cause of the following exception: Traceback (most recent call last): File "C:\AIGen\instant_id_v19\InstantID\gradio_demo\web-ui-multicontrolnet.py", line 4, in from diffusers import StableDiffusionPipeline File "", line 1075, in _handle_fromlist File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\utils\import_utils.py", line 802, in __getattr__ value = getattr(module, name) File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\utils\import_utils.py", line 802, in __getattr__ value = getattr(module, name) File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\utils\import_utils.py", line 801, in __getattr__ module = self._get_module(self._class_to_module[name]) File "C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\diffusers\utils\import_utils.py", line 813, in _get_module raise RuntimeError( RuntimeError: Failed to import diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion because of the following error (look up to see its traceback): Failed to import diffusers.loaders.lora_pipeline because of the following error (look up to see its traceback): cannot import name 'EncoderDecoderCache' from 'transformers' (C:\AIGen\instant_id_v19\InstantID\venv\lib\site-packages\transformers\__init__.py) Press any key to continue . . .