Software Engineering Courses (SECourses)•3y ago

Thanks very much for all the tutorials. They are amazing! I am looking to know how to train a mode

Thanks very much for all the tutorials. They are amazing!

I am looking to know how to train a model based on a selection of images from a photographer to capture the same tones, light and style. What would be the recommendation?

Jjohn Thanks for the welcome, specifically, would I be able to train a model based on ...

Furkan Gözükara SECourses•3/11/23, 10:25 AM

not that advanced yet

Ppheurton Thanks very much for all the tutorials. They are amazing! I am looking to know...

Furkan Gözükara SECourses•3/11/23, 10:25 AM

this video would be my recommendation to see best settings

Furkan Gözükara SECourses•3/11/23, 10:26 AM

https://youtu.be/sRdtVanSRl4

YouTubeSECourses - Software Engineering Courses

Epic Web UI DreamBooth Update - New Best Settings - 10 Stable Diffu...

RunPod: https://bit.ly/RunPodIO. Discord : https://bit.ly/SECoursesDiscord. Web UI DreamBooth got epic update and we tested all new features to find the best settings (10). 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...

Furkan Gözükara SECourses•3/11/23, 10:26 AM

moreover you can try to train with 1024x1024

MMa7adi805 do I need to pay money

Furkan Gözükara SECourses•3/11/23, 10:26 AM

runpod is paid service yes. for colab it has free option

FFurkan Gözükara SECourses runpod is paid service yes. for colab it has free option

Ma7adi805•3/11/23, 10:26 AM

ok thx

FFurkan Gözükara SECourses https://youtu.be/sRdtVanSRl4

pheurtonOP•3/11/23, 10:53 AM

Thanks Dr. Furkan, what would be your recommendation for classification images and the captions for the style?

Ma7adi805•3/11/23, 1:38 PM

RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 58982400 bytes.


Stable diffusion model failed to load, exiting
Press any key to continue . . .

RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 58982400 bytes.


Stable diffusion model failed to load, exiting
Press any key to continue . . .

MMa7adi805 ```RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. Defau...

Ma7adi805•3/11/23, 1:39 PM

how can I fix this

sickcoder•3/11/23, 1:48 PM

hi,i get black images when i try to generate images from lora trained model , i uninstalled xformers,and disabled it but no help

Ssickcoder hi,i get black images when i try to generate images from lora trained model , i ...

Ma7adi805•3/11/23, 1:56 PM

I think the checkpoint your using has something to do with the problem

MMa7adi805 how can I fix this

Ma7adi805•3/11/23, 1:57 PM

I found the problem, turns out I didn't have enough storage

Haashim•3/11/23, 2:09 PM

@Furkan Gözükara SECourses when you have to move to new pod is it best to just transfer entire SD folder using Runpodctl?

Haashim•3/11/23, 2:09 PM

or folder by folder

HHaashim @Furkan Gözükara SECourses when you have to move to new pod is it best to just t...

Furkan Gözükara SECourses•3/11/23, 3:36 PM

entire folder easier

Ppheurton Thanks Dr. Furkan, what would be your recommendation for classification images a...

Furkan Gözükara SECourses•3/11/23, 3:37 PM

i use the class token to generate classification images with cfg 7

Furkan Gözükara SECourses•3/11/23, 3:37 PM

file captions i think necessary when you want to improve quality of the model. for faces not needed. but if you want to teach full body, perhaps clothes and backgrounds can be defined if they are not different in every image

Ssickcoder hi,i get black images when i try to generate images from lora trained model , i ...

Furkan Gözükara SECourses•3/11/23, 3:38 PM

where did you train the model

FFurkan Gözükara SECourses entire folder easier

Haashim•3/11/23, 3:52 PM

Just tried, takes a very long time

Haashim•3/11/23, 3:53 PM

Wget for models is super quick

feber13•3/11/23, 4:01 PM

Hello, I have a problem with controlnet, when I put a skeletal model it gives me a black result

feber13•3/11/23, 4:01 PM

HHaashim Wget for models is super quick

Furkan Gözükara SECourses•3/11/23, 4:09 PM

yep

Ffeber13 Click to see attachment

Furkan Gözükara SECourses•3/11/23, 4:09 PM

you dont need pre processor

Furkan Gözükara SECourses•3/11/23, 4:09 PM

this is already pre processed

Furkan Gözükara SECourses•3/11/23, 4:09 PM

and that model i didnt see it

Furkan Gözükara SECourses•3/11/23, 4:09 PM

what is that one

Furkan Gözükara SECourses•3/11/23, 4:10 PM

you can watch these 2 tutorials

Furkan Gözükara SECourses•3/11/23, 4:10 PM

https://youtu.be/iFRdrRyAQdQ

YouTubeSECourses - Software Engineering Courses

Fantastic New ControlNet OpenPose Editor Extension & Image Mixing -...

Our Discord : https://discord.gg/HbqgGaZVmr. In this video, I am explaining how to use newest extension OpenPose editor and how to mix images in ControlNet. 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 #StableDiffusio...

Furkan Gözükara SECourses•3/11/23, 4:10 PM

https://youtu.be/tXaQAkOgezQ

YouTubeSECourses - Software Engineering Courses

New Style Transfer Extension, ControlNet of Automatic1111 Stable Di...

Discord : https://bit.ly/SECoursesDiscord. New fantastic style transfer feature via T2I-Adapter added to the #ControlNet extension. 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 #StableDiffusion Tutorials, #Automatic11...

playereckksdee•3/11/23, 4:56 PM

Has anyone encountered this issue with kohya ss? : raceback (most recent call last):
File "/workspace/kohya_ss-linux/venv/lib/python3.10/site-packages/gradio/routes.py", line 384, in run_predict
output = await app.get_blocks().process_api(
File "/workspace/kohya_ss-linux/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1024, in process_api
result = await self.call_function(
File "/workspace/kohya_ss-linux/venv/lib/python3.10/site-packages/gradio/blocks.py", line 836, in call_function
prediction = await anyio.to_thread.run_sync(
File "/workspace/kohya_ss-linux/venv/lib/python3.10/site-packages/anyio/to_thread.py", line 31, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "/workspace/kohya_ss-linux/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread
return await future
File "/workspace/kohya_ss-linux/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 867, in run
result = context.run(func, *args)
File "/workspace/kohya_ss-linux/lora_gui.py", line 385, in trainmodel
repeats = int(folder.split('')[0])
ValueError: invalid literal for int() with base 10: '.ipynb'

Pplayereckksdee Has anyone encountered this issue with kohya ss? : raceback (most recent call la...

Furkan Gözükara SECourses•3/11/23, 5:46 PM

i didnt use kohya yet

Furkan Gözükara SECourses•3/11/23, 5:46 PM

but dreambooth of web ui now working perfect

gatsby•3/11/23, 5:48 PM

In the 4 minute video on how to install new dreambooth extension, it is okay to stop at 3minutes? I installed dreambooth, fixed the requirements but want to access the pod though HTTP, not gradio

junsama•3/11/23, 5:53 PM

I trained my lora with kohya_ss, but after training got this error
To create a public link, set

share=True

share=True

launch()

launch()

.
Startup time: 19.1s (import gradio: 1.0s, import ldm: 0.5s, other imports: 1.3s, list extensions: 0.3s, load scripts: 0.6s, load SD checkpoint: 6.9s, create ui: 8.3s).
Failed to match keys when loading Lora /home/ubuntu/SD/stable-diffusion-webui/models/Lora/last-000009.safetensors: ['lora_unet_down_blocks_0_resnets_0_time_emb_proj.alpha', 'lora_unet_down_blocks_0_resnets_0_time_emb_proj.lora_down.weight'

junsama•3/11/23, 5:53 PM

so the keys were not matched after training

Ggatsby In the 4 minute video on how to install new dreambooth extension, it is okay to ...

Furkan Gözükara SECourses•3/11/23, 6:07 PM

sure

Furkan Gözükara SECourses•3/11/23, 6:07 PM

you can use that

FFurkan Gözükara SECourses you can use that

gatsby•3/11/23, 6:14 PM

also is the sanity sample prompt going to be using data from v1.5 to train?

gatsby•3/11/23, 6:14 PM

I mean alongside my training and class images, is the sanity sample prompt also relevant as it will be pulling sampling material to train?

Ggatsby also is the sanity sample prompt going to be using data from v1.5 to train?

Furkan Gözükara SECourses•3/11/23, 6:16 PM

no it will use your in training model

Furkan Gözükara SECourses•3/11/23, 6:16 PM

sanity is relevant to determine

Furkan Gözükara SECourses•3/11/23, 6:17 PM

model started become overtraining or not

Furkan Gözükara SECourses•3/11/23, 6:17 PM

this tutorial is really good one

gatsby•3/11/23, 6:17 PM

Oh so would it be a good idea to use the instance prompt also in the sanity prompt?

Furkan Gözükara SECourses•3/11/23, 6:17 PM

https://youtu.be/Bdl-jWR3Ukc

YouTubeSECourses - Software Engineering Courses

Zero To Hero Stable Diffusion DreamBooth Tutorial By Using Automati...

Our Discord : https://discord.gg/HbqgGaZVmr. The most advanced tutorial of Stable Diffusion Dreambooth Training. 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 ...

Ggatsby Oh so would it be a good idea to use the instance prompt also in the sanity prom...

Furkan Gözükara SECourses•3/11/23, 6:17 PM

yes

gatsby•3/11/23, 6:17 PM

Ah thanks will take a look. Keep getting confused with sanity, instance and class prompt!

bush•3/11/23, 6:36 PM

anybody have a working auto1111 webui for google colab which uses all storage of GDRIVE?

bush•3/11/23, 6:37 PM

the fast dreambooth last ben wasn't working , yesterday when i tried

Thanks very much for all the tutorials. They are amazing! I am looking to know how to train a mode

Similar Threads

Similar Threads

Similar Threads