Software Engineering Courses (SECourses)•3y ago

https://github.com/huchenlei/sd-webui-api-payload-display Make sure you either remove the package me

https://github.com/huchenlei/sd-webui-api-payload-display
Make sure you either remove the package mentions from the payloads OR
Install the package on A1111 each time where you run the API

GitHub

GitHub - huchenlei/sd-webui-api-payload-display: Display the corres...

Display the corresponding API payload after each generation on WebUI - GitHub - huchenlei/sd-webui-api-payload-display: Display the corresponding API payload after each generation on WebUI

Bbaloooo https://github.com/huchenlei/sd-webui-api-payload-display Make sure you either r...

J.•12/5/23, 6:05 PM

wow

Aandrsoe Hello, after much frustration trying to work with a1111 and controlnets, using a...

balooooOP•12/5/23, 6:05 PM

I have a few dozens of successfull payloads. The problem is that A1111 has updated several times during the last months. I have a script that does mass JSON adjustments to satisfy the updates. It's pretty annoying

J.•12/5/23, 6:06 PM

It really seems tbh that api for image generations aren't supported well

. Sad to see that it mainly just frontend guis

balooooOP•12/5/23, 6:11 PM

My workflow:

I play in GUI
Spy with the GIT package above
Do iterative improvements:
a. generations for my fine-tuned models
b. Have the script to do the analysis
c. Adjust the JSON payloads
d. repeat
After 3-5 iterations I have reached 40% success rate for different fine-tuned models

Furkan Gözükara SECourses•12/5/23, 6:28 PM

yes finally

Furkan Gözükara SECourses•12/5/23, 6:54 PM

Aldo Raine•12/5/23, 7:28 PM

what is everyones go to prompts for LinkedIn portraits?

Llucy apply_net definitely outputs what's needed for magic-animate, albeit with border...

Furkan Gözükara SECourses•12/5/23, 7:30 PM

i really improved my auto script

Furkan Gözükara SECourses•12/5/23, 7:30 PM

gonna share on patreon soon hopefully

Furkan Gözükara SECourses•12/5/23, 7:30 PM

Zono50•12/5/23, 7:49 PM

ah man can't wait for this! Excited

Zono50•12/5/23, 7:49 PM

tried installing it myself and didn't happen haha

Furkan Gözükara SECourses•12/5/23, 7:50 PM

ye so hard to make

Furkan Gözükara SECourses•12/5/23, 7:50 PM

i am testing

Furkan Gözükara SECourses•12/5/23, 7:50 PM

to announce

Zono50•12/5/23, 7:52 PM

that video is fire doc

Zono50•12/5/23, 7:52 PM

we need a dancing video of you now

Zono50•12/5/23, 7:53 PM

@Dr. Furkan Gözükara if it's not too much trouble, could you make a linux install script as well?

Furkan Gözükara SECourses•12/5/23, 8:04 PM

ZZono50 @Dr. Furkan Gözükara if it's not too much trouble, could you make a linux instal...

Furkan Gözükara SECourses•12/5/23, 8:04 PM

i will make for runpod

FiveSAI•12/5/23, 8:05 PM

Thoughts? Testing out new sdxl dreambooth settings, with a merge technique

Furkan Gözükara SECourses•12/5/23, 8:07 PM

testing 768

FFiveSAI Thoughts? Testing out new sdxl dreambooth settings, with a merge technique

Tesli23•12/5/23, 8:24 PM

link?

TTesli23 link?

FiveSAI•12/5/23, 8:24 PM

link? these are my own settings im testing

Tesli23•12/5/23, 8:25 PM

oh ok, how are you running dreambooth?

FiveSAI•12/5/23, 8:26 PM

Yep dreambooth, but suprisingly the settings somewhat work with lora too

FiveSAI•12/5/23, 8:28 PM

i've done about 600+ trainings past 2 months or so

Tesli23•12/5/23, 8:30 PM

iv'e done too many trainings as well. Are you running dreambooth in colab?

TTesli23 iv'e done too many trainings as well. Are you running dreambooth in colab?

FiveSAI•12/5/23, 8:31 PM

Nope on a 4090 on my local system

Tesli23•12/5/23, 8:31 PM

nice, i have a 4090 as well. we are the lucky ones

FiveSAI•12/5/23, 8:32 PM

Yep managed to get it before price surged like crazy

Furkan Gözükara SECourses•12/5/23, 9:36 PM

fully updated

Furkan Gözükara SECourses•12/5/23, 9:36 PM

https://www.patreon.com/posts/94098751

Furkan Gözükara SECourses•12/5/23, 9:51 PM

https://github.com/magic-research/magic-animate/issues/44

GitHub

Full Auto Installers and Instructions For Windows Including Raw Vid...

I have spent over 24 hours to prepare all these scripts You can download all from here : https://www.patreon.com/posts/94098751 Example 15 second DensePose I generated via my script 15_sec_512_clos...

740•12/5/23, 10:40 PM

missing nodes doesnt appers in manager

740•12/5/23, 10:40 PM

how can I install them

AIGambino•12/5/23, 10:46 PM

Instead of using the base sd xl for training with kohya could we use turbovisionxl for superior trainings?

Aldo Raine•12/5/23, 10:48 PM

@Dr. Furkan Gözükara I'm getting this error when Kaggle training now:
Your notebook tried to allocate more memory than is available. It has restarted.

Aldo Raine•12/5/23, 10:51 PM

that was after the first 20%/safetensor

DDR.Siva Someone help me with creating images with two different face lora

mtnmecca•12/5/23, 10:52 PM

focused on this today and so far this works. 1. Use Kohya to merge either two loras in ckpt or into one lora. 2. In adetailer use detection K of 2 with adetailer prompt similar to: person 1 <lora 1> [SEP] person 2 <lora2> 3. depending on the image generated with two people and which face has a stronger face detection then you may have to switch step 2 to get the proper detailing.