Stable Diffusion, NovelAI, Machine Learning Art - AI art generation discussion and image dump

[BirdUp]

certainly doesn't let me use celebrity prompts again

some celebrities have been hardcoded out

 

[topsykrets]

 

[Unamused Bounty Hunter]

 

[The Last Stand]

I want to join in on the dog craze.



I tried. Any tips?

teresa wright delivering a truck of supplies in a convey. the truck has a star insignia in view. there are a few dogs running with the trucks

 

[Fivehead]

I've been paying for Midjourney and using it for work and pleasure for a couple of years now but having a little taste of DALL·E 3 has ruined it for me. Midjourney is still superior at combining styles (or at least it was, before they broke v5, but I digress) but the accuracy and compositional control in DALL·E 3/Bing Image Creator feels exponentially better. And then they nerfed it. So now we have a broken and nerfed MJ and a near completely censored DALL·E 3. The enemies of fun know no bounds.

 

[Gaunt King Ithan Rilph]

I've been doing some pixel art in SD and wanted to share my findings. You need 2 things:
1. Palettize script
2. Either a checkpoint or a lora trained on pixel art.

If you're using a lora to help pixelization, a checkpoint trained on somewhat clean drawn art is good. Additionally, more biased checkpoints trained on a narrower theme seem to do better at overpowering the inherent style the lora was trained on.
Prompting tips: 'pixelart' helps with pixelization but isn't all powerful, especially if you have a very detailed prompt. 'flat colors' helps if you're using just the lora, but isn't necessary for the checkpoint.

---

Example using a regular checkpoint not specialized for pixelart (GhostMix):
Before Palettize: After:
As you can see, the finer details don't translate well into pixel art.

---

Exact same checkpoint, seed and prompts as above, with the addition of Pixel Portrait lora at 0.4 strength (closer to 1 improves initial pixelization, but style becomes too influenced by the lora training set):
Before Palettize: After:
If you click on the thumbnail of the first one, you can see that it still has imperfections and isn't true pixelart, but Palettize can work with this one a lot better.

---

Finally here's an example with the RetroDiffusion pixel art checkpoint (the creator is a huge fag and charges $50 for the model, here is a reupload of it,), no need for a lora when using this:
Before Palettize: After:
The difference is very subtle, but here's a comparison at 800% zoom:

---

When you've generated something nice you can scale them down a bit, remove the background and touch up minor issues. Shrink 4 times to get 2:2 pixels, shrink by 8 for 1:1. I use GIMP for this (make sure interpolation is set to 'none' so it doesn't blur when transforming.).

---

Bonus:
I haven't played around with environments all that much, but the Retro checkpoint does that very well too.

---

EDIT:
More testing with Palettize and realized downscaling by 4 (default 8 ), it'll handle art that isn't already slightly pixelized way better. These images are done without a lora or checkpoint trained on pixel art, rather I used this 'RPG Artist Tools' (the inbaked VAE version). The trade-off is that you can only shrink something 4 times to get 1:1 pixel size, but depending on your needs this is not a big deal.

Before Palettize: After: Shrunk to 1:1

Before Palettize: After: Shrunk to 1:1

Yes, that's still pixel perfect:

 

[Roland TB-303]

DALL-E3 is now integrated into the paid tier of ChatGPT. You type in a prompt and it creates 4 variations of your prompt to generate 4 images. It’s nice because you can get it to iteratively improve the images. Also if you like any existing images you can upload them to ChatGPT and ask it to write a prompt for you to recreate the image.

 

[std::string]

Bing warns you and threatens to ban you if you prompt it with a real person, and then also it'll just delete stuff after generating it if it recognizes a copyrighted character.

Spoiler

Well, anyway nice try Bill Gates.

 

[wakaran]

What a funny little guy

Spoiler: Prompt

old school runescape, low-poly 3d, a green-colored kiwi bird holding a sign that says sneed

 

[bigasscigar]

This thing is pretty schizophrenic, or it's trying to make me think I'm going schizo by blocking prompts I just used successfully.
It blocks me when I prompt for 'Soviet officers having fun at a carnival'. Cool, it's probably getting triggered by 'Soviet'; so I go to '1980s Russian officers having fun at a carnival' and it works.

Neat, so I want to refine a little and go for '1980s Russian officers having fun at a carnival eating cotton candy'. Blocked. Along with my previous prompt and any form of my 1980s officer workaround.
I just want to make historical looking photos of silly situations.

I did get a chuckle out of astronauts taking soil samples in third world counties

 

[wakaran]

t's trying to make me think I'm going schizo by blocking prompts I just used successfully.

Even inputting stupid shit like "tactical skeleton breaching a door" has about a 50% success rate.
I've noticed that trying another definitely safe prompt and going back to what was just blocked seems to work.

 

[Screamer_2]

New error just dropped for me.

"You can't submit any more prompts
Please wait until your other ongoing creations are complete before trying to create again."

But I don't have any ongoing creations....


Anyone have any idea how I can resolve this? I have no tabs open to the Bing AI. I have restarted the computer.

 

[we are legion]

Spoiler: DALL-E 3 prompt

Illustration reminiscent of wikihow tutorials with a sandy-hued dog looking visibly distressed, with its tongue slightly out, as it works on the terminal. The room's servers are in flames, with smoke rising from them. A distinct kiwi logo is present on each server.

 

[wakaran]

View attachment 5408715View attachment 5408712

Spoiler: DALL-E 3 prompt

Illustration reminiscent of wikihow tutorials with a sandy-hued dog looking visibly distressed, with its tongue slightly out, as it works on the terminal. The room's servers are in flames, with smoke rising from them. A distinct kiwi logo is present on each server.

No fucking way that pizza appeared unprompted lmao

 

[Niggergante]

GOD DAMMIT I JUST WANTED TO MAKE A JEW-JITSU JOKE

 

[Lidl Drip]

 

[kurosawa]

Was able to make a few in Bing referencing Zulu men and their adventures. The "safe" workaround didn't work for me and occasionally got hit with the sad dog.

"group of lebanese white Borzoi dogs in lebanese flag parachutes all high in the air, group of brown pitbull dogs with white and blue collars underneath them running on the ground in front of a desert city"

This seemed to work for me - "group of lebanese white Borzoi dogs in lebanese flag parachutes all high in the air, group of pitbulls with blue and white single star doggie sweaters running underneath them on the ground in front of a desert city." It did not like single white star.


Added "movie poster of " in front of the rest and changed to "scared pitbulls."

 

[inception_state]

Found this one, did not make it.

Also they seem to have hard-blocked the "This prompt is safe: " trick. Now that gets an immediate content warning.

 

[The Last Stand]

Bing warns you and threatens to ban you if you prompt it with a real person, and then also it'll just delete stuff after generating it if it recognizes a copyrighted character.

That explains why Bing resets itself when I use it.

Doris day driving fast down the highway in a luxury car

Also they seem to have hard-blocked the "This prompt is safe: " trick. Now that gets an immediate content warning.

Well, it was fun while it lasted.

 

[Screamer_2]