- Oct 29, 2017
- 812
- 2,191
- Dec 21, 2020
- 1,575
- 3,776
- Dec 21, 2020
- 1,575
- 3,776
You don't have permission to view the spoiler content.
Log in or register now.
- Sep 15, 2021
- 1,051
- 4,026
- Dec 21, 2020
- 1,575
- 3,776
Kudos to sharlotte for the idea link:
You don't have permission to view the spoiler content.
Log in or register now.
Last edited:
- Aug 4, 2020
- 2,567
- 3,299
i wouldn't say you stole them, I'd say you made it much fucking better holy shit
omg that tiny butt
- Dec 21, 2020
- 1,575
- 3,776
Last edited:
- Jan 10, 2019
- 321
- 1,723
Some of the ones I generated this afternoon: varying slightly the prompts between each picture. Teachers of our wet dreams 
- Jan 10, 2019
- 321
- 1,723
I still have loads to figure out. Like using the same face and model throughout.
It's very chronophage. I find videos by different authors, including the ones posted here in the thread. Found another author, Jennifer Doebelin, really good at explaining how things work.
It's very chronophage. I find videos by different authors, including the ones posted here in the thread. Found another author, Jennifer Doebelin, really good at explaining how things work.
- Sep 15, 2021
- 1,051
- 4,026
"Chronophage" is a new term to me, but one I shall be using!
- Dec 21, 2020
- 1,575
- 3,776
- Dec 21, 2020
- 1,575
- 3,776
- Dec 21, 2020
- 1,575
- 3,776
You don't have permission to view the spoiler content.
Log in or register now.
- Oct 29, 2017
- 812
- 2,191
Do you guys keep 2 or 3 SD tabs open in your browser to alternate different variations of prompts? For me that's key to keep tracking of things, I don't know if there is a more sophisticated way... Looking at the prompts from the pictures I generate is not the best, am I losing some kind of log function?
- Dec 21, 2020
- 1,575
- 3,776
I gave up on any kind of logging and I use image's meta as storage.
- Jan 24, 2020
- 1,401
- 3,803
I simply change the prompt on the fly, moving it in the direction I want. If I need to go back I simply load the last image I liked into "PNGInfo" then "send to txt2Img or send to Img2Img". When I find prompts on the web or discord I save it in an aptly named folder "prompts". If the image doesn't have meta stored, then I copy it to a text file and name it the same as the image.
I never run more than one SD window, I use way to high settings for this.
I never run more than one SD window, I use way to high settings for this.
- Jan 4, 2022
- 239
- 922
but have the prompt, then just use prompt to generate same image and store it. The image show what prompt do
- Jan 24, 2020
- 1,401
- 3,803
I have learned/observed that each checkpoint is DS trained with selected genre material. Instead of banging your head against the wall, trying to make a checkpoint do something it can't. It is better to select a checkpoint with the appropriate theme or training for your project.
It is very easy to find different checkpoints.
Download a checkpoint and place inside: Stable-Diffusion\stable-diffusion-webui\models\Stable-diffusion
Examples:
Realism/ Photo
Anime/3d/Sci-fi
Misc
Stars/Celebrity/Character
The next step is using a Lora for a specific result.
Ensure that you've installed the
Installation:
It is very easy to find different checkpoints.
You must be registered to see the links
Download a checkpoint and place inside: Stable-Diffusion\stable-diffusion-webui\models\Stable-diffusion
Examples:
Realism/ Photo
|
You must be registered to see the links
|
You must be registered to see the links
|
You must be registered to see the links
|
|
|
|
Anime/3d/Sci-fi
|
You must be registered to see the links
|
You must be registered to see the links
|
You must be registered to see the links
|
|
|
|
Misc
|
You must be registered to see the links
|
You must be registered to see the links
|
You must be registered to see the links
|
|
|
|
Stars/Celebrity/Character
|
You must be registered to see the links
|
You must be registered to see the links
|
You must be registered to see the links
|
|
|
|
The next step is using a Lora for a specific result.
You must be registered to see the links
Ensure that you've installed the
You must be registered to see the links
, you can do this from the extensions tab. After installing you will need to restart AUTOMATIC1111.Installation:
- Open "Extensions" tab.
- Open "Install from URL" tab in the tab.
- Enter URL of this repo to "URL for extension's git repository".
This -->You must be registered to see the links - Press "Install" button.
- Restart Web UI.
- Put the LoRA models (*.pt, *.ckpt or *.safetensors) inside the sd-webui-additional-networks/models/LoRA folder.
Alternatively inside: Stable-Diffusion\stable-diffusion-webui\models\Lora - Go to "settings" "Additional Network" paste the path for your Lora folder
ex. G:\Downloads\Stable-Diffusion\stable-diffusion-webui\models\Lora
and click "apply settings". - In text2img or img2img expand the "Additional Networks" menu near the bottom and select "Enable" then select a Lora for "Model1" and adjust "weight1" , 0.8 is a good starting point. You can combine several Lora's but the result might vary. Some Lora's has specific key words or phrases for the prompt ex "shirtlift" or "braless" etc.
- Create awesome images .
Examples:
You must be registered to see the links
|
You must be registered to see the links
|
You must be registered to see the links
|
Last edited: