quick question: ¿whats the advantage of using 2.1?
quick question: ¿whats the advantage of using 2.1?
Sbetter img2img, can use 768px model, more photorealistic but much worse with artistic styles and the prompts are very difficult to write for me
Sand the eyes and hands look better
Fwhat is your graphic card
Fand what is your xformers version
Fi think not much thing atm :d
Fread this
NIm training in the local webui (automatic1111)
PApparently something from the model is missing, I did something wrong Traceback (most recent call last):
File "gradio_canny2image.py", line 21, in <module>
model.load_state_dict(load_state_dict('./models/control_sd15_canny.pth', location='cuda'))
File "D:\ControlNet\cldm\model.py", line 18, in load_state_dict
state_dict = get_state_dict(torch.load(ckpt_path, map_location=torch.device(location)))
File "C:\Users\simon\AppData\Local\conda\conda\envs\control\lib\site-packages\torch\serialization.py", line 699, in load
with _open_file_like(f, 'rb') as opened_file:
File "C:\Users\simon\AppData\Local\conda\conda\envs\control\lib\site-packages\torch\serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "C:\Users\simon\AppData\Local\conda\conda\envs\control\lib\site-packages\torch\serialization.py", line 211, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: './models/control_sd15_canny.pth'
File "gradio_canny2image.py", line 21, in <module>
model.load_state_dict(load_state_dict('./models/control_sd15_canny.pth', location='cuda'))
File "D:\ControlNet\cldm\model.py", line 18, in load_state_dict
state_dict = get_state_dict(torch.load(ckpt_path, map_location=torch.device(location)))
File "C:\Users\simon\AppData\Local\conda\conda\envs\control\lib\site-packages\torch\serialization.py", line 699, in load
with _open_file_like(f, 'rb') as opened_file:
File "C:\Users\simon\AppData\Local\conda\conda\envs\control\lib\site-packages\torch\serialization.py", line 230, in _open_file_like
return _open_file(name_or_buffer, mode)
File "C:\Users\simon\AppData\Local\conda\conda\envs\control\lib\site-packages\torch\serialization.py", line 211, in init
super(_open_file, self).init(open(name, mode))
FileNotFoundError: [Errno 2] No such file or directory: './models/control_sd15_canny.pth'
SDownload the control models from here: https://huggingface.co/lllyasviel/ControlNet/tree/main/models and put them in extensions\sd-webui-controlnet\models
Pthanks
Prunning but it looks like this will take some time
P@Sesarr thanks again
Fwhen do you get this error
Fat which step like txt2img or training textual inversion
LMy Graphics card is Geforce RTX 3060 , xformers is 0.0.14 dev
Ni get it for textual inversion training, i've followed multiple tutorials but nothing seems to talk about this
Fvery good one should work very well
Fi have same 12 gb
Fi have excellent tutorial for that
Fdont enable cross optimization
Ffollow exactly as i did
FYouTubeSoftware Engineering Courses - SE Courses
Our Discord : https://discord.gg/HbqgGaZVmr. Grand Master tutorial for Textual Inversion / Text Embeddings. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on 
https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials, Automatic1111 and Google Colab Guide...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, Automatic1111 and Google Colab Guide...
Fwatch all believe me you will learn a lot
Fi just did same training on runpod still works
Fvery well
Fstill recording runpod video
LIt works well for creating images, for training it does not...
Funedited 2.5 hours atm :d
Fthis is training what you mean
LYes, I only meant it works very well for all other things except training 
NI dont have cross optimization enabled, i have tried following the tutorial and i still cant get it to work
Fmake a small video how you do so i can comment
Fonce i have time
Fi can connect your computer and set my self if you want
Ni've just tried running it again, and while i dont have the cross optimization enabled in settings and yet it appears to apply it anyways in the CMD
Fwhat was your graphic card
Fif 4gb you cant
Fmin 6 gb required
NI got a NVIDIA GeForce GTX 1070 Ti with 16 gb ram
Y¿can i get good face training, similar to dreambooth?
0Hey guys,
Sorry, I'm new. What would be the most up to date video tutorial for AUTOMATIC111 for a complete beginner? Or is there something better than AUTOMATIC111 maybe?
Sorry, I'm new. What would be the most up to date video tutorial for AUTOMATIC111 for a complete beginner? Or is there something better than AUTOMATIC111 maybe?
Fyep close
Fhey welcome
Fi have 2 great how to install and use tutorial
Ffirst watch this to do a fresh install
FYouTubeSoftware Engineering Courses - SE Courses
Our Discord : https://discord.gg/HbqgGaZVmr. How to download and install Stable Diffusion Automatic1111 Web UI interface. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials, Automatic1111 and Goog...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, Automatic1111 and Goog...
Fand watch this to learn how to use custom models
FYouTubeSoftware Engineering Courses - SE Courses
Our Discord : https://discord.gg/HbqgGaZVmr. How to use custom, different, .safetensors and SD 2.1 on Automatic1111 Web UI. If I have been of assistance to you and you would like to show your support for my work, please consider becoming a patron on https://www.patreon.com/SECourses
Playlist of Stable Diffusion Tutorials, Automatic1111 and Go...
https://www.patreon.com/SECoursesPlaylist of Stable Diffusion Tutorials, Automatic1111 and Go...
0Thanks a ton!
What's the difference between Dreambooth and SD?
What's the difference between Dreambooth and SD?
Fsd is stable diffusion the image generative model
