Software Engineering Courses (SECourses)•3y ago

So do you advice better to train with 512 x 512 pixel image and SD 1.5 model ?

So do you advice better to train with 512 x 512 pixel image and SD 1.5 model ?

© 2026 Hedgehog Software, LLC

More

Communities Docs About Terms Privacy

Reach

RReach So do you advice better to train with 512 x 512 pixel image and SD 1.5 model ?

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 2:12 PM

sd 1.5 much easier better

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 2:12 PM

also using public models are even better

ashley

A

ashley•6/6/23, 2:12 PM

W&B also helps you compare 4 different trainings to determine the optimal average epoch so you don't overtrain

Screenshot_2023-06-06_at_16.11.46.png

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 2:12 PM

according to your aim

ashley

A

ashley•6/6/23, 2:13 PM

Well can be much more than 4, just I have only done 4 so far

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 2:13 PM

W&B?

ashley

A

ashley•6/6/23, 2:13 PM

Weights & Balances (wandb.ai)

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 2:14 PM

i see paid service

ashley

A

ashley•6/6/23, 2:14 PM

You can enter your API key into Kohya_ss and EveryDream2trainer, not yet supported by Dreambooth extension but I logged a feature request to add it

Furkan Gözükara SECourses

FFurkan Gözükara SECourses i see paid service

ashley

A

ashley•6/6/23, 2:14 PM

Free for personal and academic use.

Furkan Gözükara SECourses

FFurkan Gözükara SECourses also using public models are even better

Reach

R

ReachOP•6/6/23, 2:14 PM

okay so can I use your 512 x 512 Reg class man images of your Patreon for training ?

ashley

A

ashley•6/6/23, 2:14 PM

I am not paying, I am using it for free

Reach

RReach okay so can I use your 512 x 512 Reg class man images of your Patreon for traini...

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 2:15 PM

yes. make sure that you are using the correct model

ashley

Aashley I am not paying, I am using it for free

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 2:15 PM

nice

Furkan Gözükara SECourses

FFurkan Gözükara SECourses yes. make sure that you are using the correct model

Reach

R

ReachOP•6/6/23, 2:16 PM

Yes I will use 512x512 images and SD 1.5 model for training

ashley

A

ashley•6/6/23, 2:16 PM

I will maybe pay for it if I decide to use it commercially but just running experiments at the moment, so I have a personal account

Reach

RReach Yes I will use 512x512 images and SD 1.5 model for training

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 2:51 PM

yep

frandagostino

F

frandagostino•6/6/23, 3:35 PM

Dear, how are you? Anyone tried training Textual Inversion on an Apple M2 at a reasonable training time?

Zono50

Z

Zono50•6/6/23, 3:36 PM

generated samples using the adan adaption optimizer using learning rate of 1e-3 and 5-e5 and get this

frandagostino

F

frandagostino•6/6/23, 3:36 PM

I've a Macbook M2 16GB, is it viable or should I go with Colab/Runpod/etc?

Zono50

ZZono50 generated samples using the adan adaption optimizer using learning rate of 1e-3 ...

ashley

A

ashley•6/6/23, 3:43 PM

I think the guy on D8ahazard Dreambooth who already answered you is the only person who has experience using this stuff properly

ashley

A

ashley•6/6/23, 3:43 PM

The new optimizers are too new, not many people know how to use them yet.

ashley

A

ashley•6/6/23, 3:44 PM

Especially when the release notes have incorrect instructions on how to use them

LeHeL

L

LeHeL•6/6/23, 3:55 PM

I want to make a software in PHP to call A1111 (or raw SD) in which to call through the software API.
What it should do is to generate a mix from 2 images. So I'm thinking of an img2img in which I give img as input and net control or swap as the second image.
In fact, what I want is to make some stylized images (like a poster) in which I can swap faces with an uploaded face.
Does anyone have an idea how I could do this through the API?

LeHeL

LLeHeL I want to make a software in PHP to call A1111 (or raw SD) in which to call thro...

ashley

A

ashley•6/6/23, 3:57 PM

visit the A1111 URL and add

/docs

/docs

to the end of it to see API documentation.
Also enable

--api

--api

in your launch command in

web-user.*

web-user.*

ashley

A

ashley•6/6/23, 3:58 PM

For img2img, the payload looks like this:

    sd_payload = {
        'init_images': [
            image_content
        ],
        'resize_mode': 0,
        'denoising_strength': payload['denoising_strength'],
        'image_cfg_scale': 0,
        'prompt': payload['positive_prompt'],
        'seed': -1,
        "sampler_name": payload['sampler'],
        'batch_size': payload['batch_size'],
        'n_iter': 1,
        'steps': payload['steps'],
        'cfg_scale': payload['cfg_scale'],
        'width': width,
        'height': height,
        'restore_faces': True,
        'tiling': False,
        'do_not_save_samples': False,
        'do_not_save_grid': False,
        'negative_prompt': payload['negative_prompt'],
        'eta': 0,
        's_churn': 0,
        's_tmax': 0,
        's_tmin': 0,
        's_noise': 1,
        'sampler_index': payload['sampler'],
        'include_init_images': False,
        'send_images': True,
        'save_images': False,
    }

    sd_payload = {
        'init_images': [
            image_content
        ],
        'resize_mode': 0,
        'denoising_strength': payload['denoising_strength'],
        'image_cfg_scale': 0,
        'prompt': payload['positive_prompt'],
        'seed': -1,
        "sampler_name": payload['sampler'],
        'batch_size': payload['batch_size'],
        'n_iter': 1,
        'steps': payload['steps'],
        'cfg_scale': payload['cfg_scale'],
        'width': width,
        'height': height,
        'restore_faces': True,
        'tiling': False,
        'do_not_save_samples': False,
        'do_not_save_grid': False,
        'negative_prompt': payload['negative_prompt'],
        'eta': 0,
        's_churn': 0,
        's_tmax': 0,
        's_tmin': 0,
        's_noise': 1,
        'sampler_index': payload['sampler'],
        'include_init_images': False,
        'send_images': True,
        'save_images': False,
    }

LeHeL

L

LeHeL•6/6/23, 3:58 PM

Yeah, I know that but dunno if I can add face swap addon az API call.

ashley

A

ashley•6/6/23, 3:58 PM

where image_content is base64 encoded binary content of the image

LeHeL

L

LeHeL•6/6/23, 3:59 PM

tx

ashley

A

ashley•6/6/23, 3:59 PM

to add ControlNet:

sd_payload['alwayson_scripts'] = {
                'controlnet': {
                    'args': [
                        {
                            'module': 'canny',
                            'model': 'control_sd15_canny [fef5e48e]',
                            'weight': 1,
                            'resize_mode': 'Crop and Resize',
                            'lowvram': False,
                            'processor_res': 512,
                            'threshold_a': 75,
                            'threshold_b': 75,
                            'guidance': 1,
                            'guidance_start': 0,
                            'guidance_end': 1,
                            'control_mode': "Balanced",
                            'pixel_perfect': False
                        }
                    ]
                }
            }

sd_payload['alwayson_scripts'] = {
                'controlnet': {
                    'args': [
                        {
                            'module': 'canny',
                            'model': 'control_sd15_canny [fef5e48e]',
                            'weight': 1,
                            'resize_mode': 'Crop and Resize',
                            'lowvram': False,
                            'processor_res': 512,
                            'threshold_a': 75,
                            'threshold_b': 75,
                            'guidance': 1,
                            'guidance_start': 0,
                            'guidance_end': 1,
                            'control_mode': "Balanced",
                            'pixel_perfect': False
                        }
                    ]
                }
            }

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:05 PM

anyone have any idea of this error https://github.com/Mikubill/sd-webui-controlnet/issues/1573

GitHub

FileNotFoundError: [Errno 2] - works but result not displayed in gr...

Is there an existing issue for this? I have searched the existing issues and checked the recent builds/commits of both this extension and the webui What happened? Just made a fresh installation The...

FileNotFoundError: [Errno 2] - works but result not displayed in gr...

LeHeL

LLeHeL I want to make a software in PHP to call A1111 (or raw SD) in which to call thro...

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:06 PM

api is something very less covered. never tried personally but you should be able to make

Furkan Gözükara SECourses

FFurkan Gözükara SECourses api is something very less covered. never tried personally but you should be abl...

ashley

A

ashley•6/6/23, 4:10 PM

Yes he can do it, I have done it, also done for Dreambooth

ashley

A

ashley•6/6/23, 4:11 PM

A1111 API is more stable than Dreambooth API, the Dreambooth API to get status is broken

ashley

A

ashley•6/6/23, 4:11 PM

But everything Dreambooth is unstable

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:12 PM

if i needed it in a business

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:12 PM

i would use the script diredtly

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:12 PM

not via api of auto1111

ashley

A

ashley•6/6/23, 4:15 PM

Yeah I think thats what Fast Stable Diffusion by TheLastBen does, and thats what RunPod use in their ridiculously expensive dreambooth API endpoint.

ashley

Aashley Yeah I think thats what Fast Stable Diffusion by TheLastBen does, and thats what...

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:19 PM

do you have any idea regarding this : https://github.com/Mikubill/sd-webui-controlnet/issues/1573

GitHub

FileNotFoundError: [Errno 2] - works but result not displayed in gr...

Is there an existing issue for this? I have searched the existing issues and checked the recent builds/commits of both this extension and the webui What happened? Just made a fresh installation The...

FileNotFoundError: [Errno 2] - works but result not displayed in gr...

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:19 PM

this happened on a patreon supporter

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:19 PM

i just did a fresh install

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:19 PM

definitely some caching issue

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:27 PM

solution found

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:27 PM

playereckksdee

P

playereckksdee•6/6/23, 4:29 PM

Anyone have kohya ss settings that give similar output to dreambooth?

Furkan Gözükara SECourses

FFurkan Gözükara SECourses solution found

ashley

A

ashley•6/6/23, 4:29 PM

What was the solution?

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:35 PM

https://github.com/Mikubill/sd-webui-controlnet/issues/1563

GitHub

[Bug]: FileNotFoundError: [Errno 2]... tmp2514rfci.png' · Issue #15...

Is there an existing issue for this? I have searched the existing issues and checked the recent builds/commits of both this extension and the webui What happened? Hello! since last update(today) go...

[Bug]: FileNotFoundError: [Errno 2]... tmp2514rfci.png' · Issue #15...

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:35 PM

Just running any generated image with any model using controlnet and no embeddings showed this. I actually just fixed it by adding a gradio folder to my temp location. Not sure why it wasnt automatically generating this.

C:\Users"Username"\AppData\Local\Temp

Furkan Gözükara SECourses

F

Furkan Gözükara SECourses•6/6/23, 4:48 PM

this realism amazing

    sd_payload = {
        'init_images': [
            image_content
        ],
        'resize_mode': 0,
        'denoising_strength': payload['denoising_strength'],
        'image_cfg_scale': 0,
        'prompt': payload['positive_prompt'],
        'seed': -1,
        "sampler_name": payload['sampler'],
        'batch_size': payload['batch_size'],
        'n_iter': 1,
        'steps': payload['steps'],
        'cfg_scale': payload['cfg_scale'],
        'width': width,
        'height': height,
        'restore_faces': True,
        'tiling': False,
        'do_not_save_samples': False,
        'do_not_save_grid': False,
        'negative_prompt': payload['negative_prompt'],
        'eta': 0,
        's_churn': 0,
        's_tmax': 0,
        's_tmin': 0,
        's_noise': 1,
        'sampler_index': payload['sampler'],
        'include_init_images': False,
        'send_images': True,
        'save_images': False,
    }

    sd_payload = {
        'init_images': [
            image_content
        ],
        'resize_mode': 0,
        'denoising_strength': payload['denoising_strength'],
        'image_cfg_scale': 0,
        'prompt': payload['positive_prompt'],
        'seed': -1,
        "sampler_name": payload['sampler'],
        'batch_size': payload['batch_size'],
        'n_iter': 1,
        'steps': payload['steps'],
        'cfg_scale': payload['cfg_scale'],
        'width': width,
        'height': height,
        'restore_faces': True,
        'tiling': False,
        'do_not_save_samples': False,
        'do_not_save_grid': False,
        'negative_prompt': payload['negative_prompt'],
        'eta': 0,
        's_churn': 0,
        's_tmax': 0,
        's_tmin': 0,
        's_noise': 1,
        'sampler_index': payload['sampler'],
        'include_init_images': False,
        'send_images': True,
        'save_images': False,
    }

sd_payload['alwayson_scripts'] = {
                'controlnet': {
                    'args': [
                        {
                            'module': 'canny',
                            'model': 'control_sd15_canny [fef5e48e]',
                            'weight': 1,
                            'resize_mode': 'Crop and Resize',
                            'lowvram': False,
                            'processor_res': 512,
                            'threshold_a': 75,
                            'threshold_b': 75,
                            'guidance': 1,
                            'guidance_start': 0,
                            'guidance_end': 1,
                            'control_mode': "Balanced",
                            'pixel_perfect': False
                        }
                    ]
                }
            }

sd_payload['alwayson_scripts'] = {
                'controlnet': {
                    'args': [
                        {
                            'module': 'canny',
                            'model': 'control_sd15_canny [fef5e48e]',
                            'weight': 1,
                            'resize_mode': 'Crop and Resize',
                            'lowvram': False,
                            'processor_res': 512,
                            'threshold_a': 75,
                            'threshold_b': 75,
                            'guidance': 1,
                            'guidance_start': 0,
                            'guidance_end': 1,
                            'control_mode': "Balanced",
                            'pixel_perfect': False
                        }
                    ]
                }
            }