[Stable Diffusion] Prompt Sharing and Learning Thread

[Synalon]

Anyone able to show me how to set up a static seed on comfy ui, step by step please I'm stupid.

 

[me3]

Anyone able to show me how to set up a static seed on comfy ui, step by step please I'm stupid.

i don't have access to the UI atm, but generally in the seed/sampler node you have 2 fields, one for the seed number and a text/select one, can't remember the wording on it but when you click it you get the option to select "fixed". Default is some wording of "random seed after generation"

 

[Synalon]

i don't have access to the UI atm, but generally in the seed/sampler node you have 2 fields, one for the seed number and a text/select one, can't remember the wording on it but when you click it you get the option to select "fixed". Default is some wording of "random seed after generation"

Thanks I'll take a look. Do you also know how to use extensions in ComfyUi, such as Adetailer?

 

[me3]

Thanks I'll take a look. Do you also know how to use extensions in ComfyUi, such as Adetailer?

Fraid not, i've only done some limited screwing around with comfy.
Trying to find consistency in training and getting one "generator" to cooper is taking enough time, specially on a slow spec comp, so haven't really had the time to do much with comfy.

The nightmare of trying to pick the best out of a training.... Generally you hope for a bunch of poor results and one that stands out, this grid is among the more varied ones for this training....the closeup face shot grid is hopeless to figure out



(great, image gets resized, probably due to width i guess, it's barly over 15k px....kinda makes it a bit pointless )

 

[Sepheyer]

Anyone able to show me how to set up a static seed on comfy ui, step by step please I'm stupid.

Using same seed in ComfyUI:

 

[Sepheyer]

Cycle Through Models / Samplers in ComfyUI

Say you want to use same seed but cycle through samplers:

1. Right click on "KSampler", then chose convert sampler_name to input.
2. Add node called "primitive" to the workspace.
3. Connect the node "primitive" to the "sampler_name" of the KSampler - you will see how this node "primitive" changes its look and gets additional fields.
4. Change the field "control_after_generate" in the node "primitive" to "increment".

The setup should look like this:

 

[Mr-Fox]

negative prompts are much less needed than ppl think, you're generally better off starting without them and being specific in your positive prompt.
IE using age to avoid the person being too young or old, or the type and quality of photo.
Negatives mostly come into play to combat "conflicts", like when you're specifying colors that has a habit of coloring everything or the switching place with another color. In those cases you'd use negatives to "disallow" the color on the specific thing.
Alot of these "easy this and that" flood prompts with pointless instructions which most likely has negative impacts on your image. One very basic example would be if you're trying to create something that's dirty, in ruins, "dystopian" etc, and your "easy to use prompting" contains negatives like ugly and/or old.

Start with a simple positive prompt, find the basics you want and work on finding a specific seed you like (optional in many cases), then tweak/expand upon your positive prompt and if you encounter persisting "problems" you can start trying to add some very specific negative prompts.

With the, worryingly high, amount of images i've generated so far i'm seeing very clear signs that negative prompts are byfar less needed than "guides" and "all knowing super important creators" make it out to be.
As Mr-Fox mentioned, stick to the good old

You must be registered to see the links

I agree with most what you said but I also completely disagree.. I think that negative prompting is a very powerful tool if you utilize it properly and is very much essential. Easy negative and the likes is a bad and lazy way to go about it though. It's a bit like hitting SD over the head repeatedly while screaming "make nice picture" over and over and think this will get you what you want. Negative prompting is not only for "conflicts", it's all about tags for what you don't want to see in your image, but also a way to "guide" the image in the right direction. It becomes especially powerful when used in combination with the positive tags.

Example

pos: huge boobas
neg: small boobas

Now by utilizing the neg you have increased the weight for huge boobas substantially.

Example2

pos: photography
neg: cartoon, painting, 3D, Render, Anime, Hentai, sketch etc

Now you have specified the image medium much more clearly.

Negative prompting is very much an essential part of generating ai images, just need to utilize it in a good way and not use neg lora's or Ti's etc.

 

[me3]

I'm gonna take the risk that the previous image posting was due to no prompts, apologies if it wasn't. So fingers crossed i'm not pissing off creators, mods and everything.

Spoiler: prompts

You don't have permission to view the spoiler content. Log in or register now.

 

[Mr-Fox]

I'm gonna take the risk that the previous image posting was due to no prompts, apologies if it wasn't. So fingers crossed i'm not pissing off creators, mods and everything.
View attachment 2841196 View attachment 2841197 View attachment 2841198

Spoiler: prompts

You don't have permission to view the spoiler content. Log in or register now.

I loved holiday island and especially Yvette. Before training my Kendra Lora I made a failed attempt at an Yvette Lora.
Try your prompt with Kendra, it should give some interesting result. You probably need to use a low weight and possibly adjust the prompt a bit. She is quite thick in comparison with Yvette but if you adapt the prompt you will get the huge boobas from her.

You must be registered to see the links

 

[Mr-Fox]

I'm gonna take the risk that the previous image posting was due to no prompts, apologies if it wasn't. So fingers crossed i'm not pissing off creators, mods and everything.
View attachment 2841196 View attachment 2841197 View attachment 2841198

Spoiler: prompts

You don't have permission to view the spoiler content. Log in or register now.

I created an image of Yvette way back with img2img, before I really had a clue.

Spoiler: Prompt

You don't have permission to view the spoiler content. Log in or register now.

And also Dr Rosario, that I never posted here.

Spoiler: Prompt

You don't have permission to view the spoiler content. Log in or register now.

 

[FreakyHokage]

It's made with an extension called roop, not a lora.

You must be registered to see the links

Follow the installation instruction, it won't work otherwise. After the installation you need to edit a code inside a py file to turn off the NSFW filter. In Stable-Diffusion\stable-diffusion-webui\extensions\sd-webui-roop\scripts edit cimage.py and replace the code with this:
" import tempfile
def convert_to_sd(img):
return [False, tempfile.NamedTemporaryFile(delete=False, suffix=".png")] "

Thanks for info

 

[me3]

If you didn't know where it was from, i guess it wouldn't be too bad a picture...

Spoiler: Prompt

You don't have permission to view the spoiler content. Log in or register now.

As i think about it, it was a bit disrespectful to not credit darkhound1 as creator of the "base" images in the previous post so i better mention it this time

 

[Synalon]

Cycle Through Models / Samplers in ComfyUI

Say you want to use same seed but cycle through samplers:

1. Right click on "KSampler", then chose convert sampler_name to input.
2. Add node called "primitive" to the workspace.
3. Connect the node "primitive" to the "sampler_name" of the KSampler - you will see how this node "primitive" changes its look and gets additional fields.
4. Change the field "control_after_generate" in the node "primitive" to "increment".

The setup should look like this:

View attachment 2840848

Thanks for this, I found the fixed seed eventually but didn't know about the sampler

 

[Synalon]

I've managed to add a lora to my workflow and I'm wondering if its possible to add multiple lora nodes?

After that is adding controlnet and detailer/impact for the hands and face and I'll finally switch to comfyui.

 

[Sepheyer]

I've managed to add a lora to my workflow and I'm wondering if its possible to add multiple lora nodes?

After that is adding controlnet and detailer/impact for the hands and face and I'll finally switch to comfyui.

If you are using ComfyUI then here's a workflow with two loras and OpenPoses control net:

https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-11088119

 

[Synalon]

If you are using ComfyUI then here's a workflow with two loras and OpenPoses control net:

https://f95zone.to/threads/stable-diffusion-prompt-sharing-and-learning-thread.146036/post-11088119

Thanks this is a big help.

 

[rogue_69]

In my never-ending quest to figure out how to do things that have almost no use-case, I present a 360 spherical Stable Diffusion/Daz Studio Hybrid.

Spoiler: My Workflow

You don't have permission to view the spoiler content. Log in or register now.

 

[Mr-Fox]

In my never-ending quest to figure out how to do things that have almost no use-case, I present a 360 spherical Stable Diffusion/Daz Studio Hybrid.
View attachment 2848319

Spoiler: My Workflow

You don't have permission to view the spoiler content. Log in or register now.

It's nice and all, but can you please explain for us plebs what this is for? How do we view it? What is the use case scenario?

 

[Deleted member 5302499]

Any Linux user here that can help me with an error that I'm getting trying to run SD?:
This is the last line and the UI never opens:
ModuleNotFoundError: No module named '_bz2'

 

[Synalon]

It's a python error I know that much at least, I don't use Linux but maybe reinstalling python will fix it.