In Depth Tutorial: Unlimited Lensa AI Avatars FREE–Stable Diffusion on Any Computer

preview_player
Показать описание
Lensa has made millions of $$ dollars off an internet fad, and they don't even produce the part of their software that makes it run. They are re-packaging an open-source piece of software that you can run on your own computer: Stable Diffusion. In this video, I walk you through using stable diffusion to generate the same cool AI art that Lensa charges you for–unlimited and all for free. Use this to market your business if you're an entrepreneur!

#aiavatar #entrepreneur #stablediffusion

Рекомендации по теме
Комментарии
Автор

After watching tones of tutorials, and ending up with shitty results always, your tutorial is the only one that gave me the best result ever! you deserve a sub <3

balsamnasa
Автор

Thank you for this, do you know if there is a new version of this since SDXL came out?

JLisk
Автор

the 'Install xformers from precompiled wheel.' step is giving me the error '...is not a supported wheel on this platform.' -- any suggestions?

slouchsock
Автор

Hey, in my settings, the 3 instance inputs and class input lines are missing (so I can't define where I have my photos or what type they are), am I doing something wrong maybe?

Niphiz
Автор

i got error >> ERROR: is not a supported wheel on this platform.

:((

TheIslamMessage
Автор

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
torch 2.0.1+cu118 requires triton==2.0.0; platform_system == "Linux" and platform_machine == "x86_64", but you have triton 2.1.0 which is incompatible.

tse
Автор

Also thank you so so much as I finally got to train a model on my self and my dog and it turned out so good.

IDFHELL
Автор

My computer's GPU is quite old, I doubt it can run Stable Diffusion Web UI (I tried it, didn't work) My question is once the model is trained and I have the ckpt file, how can I use the New Lil Assistance AI without going through all the steps to recreate the model and instead use the one I have already created in the Google Drive link. Your code says in one function - # If you want to use previously trained model saved in gdrive, replace this with the full path of model in gdrive

How do I use a previously trained model. I tried replacing WEIGHTS_DIR with the Google Drive model link but it didn't work.

bauljgd
Автор

now when i try it today i get this error:
TypeError: unwrap_model() got an unexpected keyword argument 'keep_fp32_wrapper'

is it still working on your workflow?

mrx
Автор

Hey man, I have a problem at the training step at 6:03 . Tg error says « the following values were not passed to »

YanisB-lzek
Автор

The ckpt file does not show up in my google drive :(

patrykturski
Автор

i get an error when i -Run to generate a grid of preview images from the last saved weights.

IndexError: list index out of range

rongutman
Автор

I am getting the below error


IndexError Traceback (most recent call last)
in <module>
8
9 row = len(folders)
---> 10 col = len(os.listdir(os.path.join(weights_folder, folders[0], "samples")))
11 scale = 4
12 fig, axes = plt.subplots(row, col, figsize=(col*scale, row*scale), gridspec_kw={'hspace': 0, 'wspace': 0})

IndexError: list index out of range

EngineerGamer
Автор

im getting this error
ERROR: is not a supported wheel on this platform.

janathwijesinghe
Автор

i do everything exactly as you do but i keep getting errors when the ai is training the photos..What do i do?

EricBwire
Автор

getting error - /bin/bash: accelerate: command not found (in accelerate launch which comes after uploading photos)

sbmeta
Автор

I followed steps exactly, every thing went good but the output just my face, i uploaded viking prompt, changing name in dir(instacdir, class namee...) Uploading prompt giving prompt where the only inputs i gave, what might be the issue?

deeku
Автор

How come you used "lil" in the setup steps but I kept seeing you enter "lile" in the prompts (even though you were still saying "lil"?

oranghill
Автор

Thank you very much for the great tutorial.
Is there any way to use lora model with this?

lahiruwijesinghe
Автор

A new error came up today.. The wheel isn't supported anymore

brewtime