[Stable Diffusion] Prompt Sharing and Learning Thread

[Mr-Fox]

Yes, you render your image first from txt2img, then img2img.

I'm also very fond of using Hires.fix, but in this case it's not possible, because you have to render an image twice as big as the default 512 or 768, which most models use.

first create your image with a simple prompt:
"glamour shot photo of a beautiful woman walking down a tropical beach in a skimpy bikini"
512 x 768
View attachment 2773438

After that you send it to img2img:
Put the image in controlnet an activate inpaint using impaint+lama as preprocessor, it's very important to put resize mode to "Resize and fill".

use a denoise between 0.75 to 1 and use your favorite widescreen size, in this case a 16:9
View attachment 2773452

This will create an image from 512x768 to 1368x768 (16:9)

that is why is not possible to use Hires, because it will try to create from a 1024x1536 (if using x2 hires) to 2048x1536, it will take forever to render and the result will be terrible, I tried.

Probably you will have to try a few times before you get a satisfying image,

this was my first try:

use inpaint to fix any error

After that, you can use your favorite upscaler and do a final inpaint retouch
View attachment 2773495

Thank you very much for the help. I will look into this.

 

[sharlotte]

Dagg0th that's a great post - should be added to the first page. I saw a video on this, again by S Kamph:

You must be registered to see the links

, which is also very valuable.

Meantime, i've tried to see what I could do, panorama wise based on your prompt me3 (I did some modification on the sampling and some other sliders) , with my GC (not boasting, could only afford a RTX3060 (a MSI Ventus) with 12gb vram) - and added Mr-Fox favourite Hi-res onto it. Here are some of the results I got, no rework and I can do 4096*1024 (have not tried to push the height further):

 

[Sepheyer]

Dagg0th that's a great post - should be added to the first page. I saw a video on this, again by S Kamph:

You must be registered to see the links

, which is also very valuable.

Meantime, i've tried to see what I could do, panorama wise based on your prompt me3 (I did some modification on the sampling and some other sliders) , with my GC (not boasting, could only afford a RTX3060 (a MSI Ventus) with 12gb vram) - and added Mr-Fox favourite Hi-res onto it. Here are some of the results I got, no rework and I can do 4096*1024 (have not tried to push the height further):
View attachment 2774257 View attachment 2774258 View attachment 2774259

Good call. I added that OG's post into the links section.

 

[sharlotte]

Some more landscapes with high res:

 

[Mr-Fox]

Awesome guys, you're doing the lords work.

 

[me3]

I can't check the prompts in sharlotte's images right now so not sure if it's already in there, but in a basic way the delayed "subject" gets put into "empty" spots in the generation. Keep in mind that's empty for the AI in that specific step, not what we would consider empty space in the finished image. So a simple -/+ 1 in steps can change quite a bit.
Also, layering the image can give some nice results. IE start drawing the background, then the subject and finish off with including the foreground.

The two "mushroom" images i posted here uses some of it if i remember correctly.

 

[sharlotte]

My apologies if this has been covered already (I did a search but could not find it). I started messing around with latent couple.
So first installed the two extensions as per the below (

You must be registered to see the links

and make sure to select the

You must be registered to see the links

, there's another one but it does not have the ability to add a sketch).


Once done, you may need to restart the gui.
In my case, I just used paint and created a frame like this making sure that each 'square' (you can use whatever you want) is coloured in different colours (important for the latent couple to identify the different sections later).
Once that's done, in your text to image, enable both composable lora and latent couple and upload your sketch like so:

Once done, click on 'i've finished my sketch' and you will see an area for the general prompt and for each sub-prompt relating to each coloured section you defined in your sketch. Fill them all in with the required info as per the below:

and once done, click on 'prompt info update'.
This will populate your positive prompt and you're ready to go.

I generated the below, using hi-res (png contains generative info as usual). It took a while (less than 30 secs without hi-res, close to 40 minutes with hires (...)) but that maybe my prompts and selections (i'll test more to check that).

on the below (hires) I may have wanted to add some negative prompts (forgot as I was excited to try it out....)


Below without hires:


Sorry for the long post but wanted to share

 

[Synalon]

Any good prompts or tools/extensions that will allow me to make a character hold a gun?

 

[Mr-Fox]

My first attempt, following both the instructions of Dagg0th and Sharlotte. Thank you both for the help.
Since I already had this prompt going, i'm using my modified version of Sharlotte's gorgeous prompt.

Spoiler: Prompt Image

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

 

[Mr-Fox]

Any good prompts or tools/extensions that will allow me to make a character hold a gun?

I would start my search by looking at Lora's or Ti's on civitai. As for tools/extensions, controlnet openpose is your best bet.

 

[Mr-Fox]

I would start my search by looking at Lora's or Ti's on civitai. As for tools/extensions, controlnet openpose is your best bet.

Sebastian Kamph Tutorial, new controlnet 1.1:

You must be registered to see the links

(not gun related but it's a start).
I'm thinking that if you can pose the subject and add a gun in the prompt hopefully SD can connect them together in the image
There is also things like regional prompting and latent couple, maybe this is necessary for giving SD some help. It is extensions that tells SD where in the image the prompt is relevant. So potentially you could place the gun in the hand of the subject this way.
On civitai there are ready made poses for the openpose editor. This is also something to look into. I would search for action poses.

 

[Mr-Fox]

My apologies if this has been covered already (I did a search but could not find it). I started messing around with latent couple.
So first installed the two extensions as per the below (

You must be registered to see the links

and make sure to select the

You must be registered to see the links

, there's another one but it does not have the ability to add a sketch).
View attachment 2777548

Once done, you may need to restart the gui.
In my case, I just used paint and created a frame like this View attachment 2777553 making sure that each 'square' (you can use whatever you want) is coloured in different colours (important for the latent couple to identify the different sections later).
Once that's done, in your text to image, enable both composable lora and latent couple and upload your sketch like so: View attachment 2777552

Once done, click on 'i've finished my sketch' and you will see an area for the general prompt and for each sub-prompt relating to each coloured section you defined in your sketch. Fill them all in with the required info as per the below: View attachment 2777551

and once done, click on 'prompt info update'.
This will populate your positive prompt and you're ready to go.
View attachment 2777572
I generated the below, using hi-res (png contains generative info as usual). It took a while (less than 30 secs without hi-res, close to 40 minutes with hires (...)) but that maybe my prompts and selections (i'll test more to check that).

on the below (hires) I may have wanted to add some negative prompts (forgot as I was excited to try it out....)
View attachment 2777573

Below without hires:
View attachment 2777574 View attachment 2777575

Sorry for the long post but wanted to share

I found a very interesting video about this. It's not so much a tutorial imo but more a proof of concept. The guy is mumbling a bit too much and it's almost impossible to see the setting on his screen. It's very interesting nonetheless.

You must be registered to see the links

 

[Synalon]

I also managed to get a widescreen image following Daggoths' instructions, the waterfall on the left didn't come out as well as I wanted but its a start. I'm trying to get a mix between a painting and photo, I kind of like how this looks.

 

[Dagg0th]

Crazy about the timing but here is a new video from SahiNama about the widescreen methond using inpaint+lama in controlnet.

You must be registered to see the links

I just recently create another example in this thread
https://f95zone.to/threads/ai-art-show-us-your-ai-skill.138575/post-11257055

 

[Mr-Fox]

Crazy about the timing but here is a new video from SahiNama about the widescreen methond using inpaint+lama in controlnet.

You must be registered to see the links

I just recently create another example in this thread
https://f95zone.to/threads/ai-art-show-us-your-ai-skill.138575/post-11257055

Now this is how you make a tutorial.

 

[Mr-Fox]

View attachment 2778864
I also managed to get a widescreen image following Daggoths' instructions, the waterfall on the left didn't come out as well as I wanted but its a start. I'm trying to get a mix between a painting and photo, I kind of like how this looks.

Try switching to "my prompt is more important", see wich of the 3 is best. Play with "denoising strength". Start with 1.0 and lower it in 0.05 increments. don't go lower than 0.8 . Play with "Control Weight" and "Ending control step" .
Don't forget to do a normal img2img generation to smooth out the "seems" . Even in this stage it's a good idea to play around with denoising strength, 0.4-0.6 is recommended but don't let that stop you from trying values outside this.

 

[Mr-Fox]

Sebastian Kamph Tutorial, new controlnet 1.1:

You must be registered to see the links

(not gun related but it's a start).
I'm thinking that if you can pose the subject and add a gun in the prompt hopefully SD can connect them together in the image
There is also things like regional prompting and latent couple, maybe this is necessary for giving SD some help. It is extensions that tells SD where in the image the prompt is relevant. So potentially you could place the gun in the hand of the subject this way.
On civitai there are ready made poses for the openpose editor. This is also something to look into. I would search for action poses.

There's also depthmaps I belive it's called that can be used. It's like those coloring books that has the outlines in black and you then fill in the color. It means that you can make a "sketch" that you will then use with controlnet. Sebastian Kamph has used this technique I believe in his tutorials about controlnet. Aitrepeneur has similar videos.

Example:

 

[Mr-Fox]

I followed the instructions from this video about controlnet 1.1 by Sebastian Kamph

You must be registered to see the links

I created a quick pose with

You must be registered to see the links

and used it with controlnet openpose.
This is only an example or proof of concept:

 

[me3]

Just something i remembered i thought might be worth pointing out that it might not be logical/obvious.
It seems that when you use the words "realistic" or variations of it, the AI doesn't interpret it the same way we might be.
In most cases the it's applied in the sense you'd have a "fake" image/scene from something (basically cgi, drawn, painted etc) that's meant to have a sense of a "real" feel to it. However it's NOT the detail/quality "likeness" of what a photograph would be.
So if you're trying to make something that's meant to be a photo and/or things of that nature with color depth, quality, detail, etc, you should probably NOT include "realistic" in your positive prompt, it might be better off in negative.

 

[Mr-Fox]

Just something i remembered i thought might be worth pointing out that it might not be logical/obvious.
It seems that when you use the words "realistic" or variations of it, the AI doesn't interpret it the same way we might be.
In most cases the it's applied in the sense you'd have a "fake" image/scene from something (basically cgi, drawn, painted etc) that's meant to have a sense of a "real" feel to it. However it's NOT the detail/quality "likeness" of what a photograph would be.
So if you're trying to make something that's meant to be a photo and/or things of that nature with color depth, quality, detail, etc, you should probably NOT include "realistic" in your positive prompt, it might be better off in negative.

Yes, you're spot on. I have also noticed this. In order to get something lifelike or based in reality use phrases like photography and specify what type it is. For example glamour photo or artistic photography, professional photo etc. Time of day and light conditions etc.
Also use camera specs and descriptive terms used in photography. Terms describing composition etc. If you use descriptive terms used in rendering or videogame engines, you will get visuals more towards 3d, CGI or rendering. The same goes for animation and cartoons etc. If this is what you want, use appropriate terms.