Check our Automatic111. Read the GitHub read me. It has install instructions for all operating systems. You’ll need a fairly powerful computer to generate these at a reasonable speed.
Check our Automatic111. Read the GitHub read me. It has install instructions for all operating systems. You’ll need a fairly powerful computer to generate these at a reasonable speed.
Thank you for your helpful tips and explanations! I find it hard to “paint” with my mouse but I guess a rough outline is enough to help the prompt do it’s work.
Well done! Did you inpaint to remove clothing?
It’s really easy in Automatic111 in the checkpoint merge tab. Just search for checkpoint merge and you’ll find a tutorial.
Wonderful write up! Thanks for sharing all the intermediary pictures. The tit hand is hilarious.
I was especially impressed with your shaded inpainting. I didn’t know you could do that. You selected the different colors? I guess you found that using a little more sophisticated shading colors got you better results than painting over everything black? Inpainting is still a bit mysterious to me.
It’s a mix of Realistic Vision 4, LazyMix+, and URPM.
Lol. Hilarious. Looking forward to your future creations and creativity.
These are really good! I love the on/off juxtaposition you achieved with inpainting.
When you inpainted, did you change the prompt? Did you alter the clothing/style to nude? Did you paint over just the body region? Did you apply LoRa’s? Can you give a bit more details in your process? I would like to do something similar with future generations.
Anyway, this is 10/10 stuff.
Nice take on this one!
The space race should win. These are hilariously good and creative.
Some mysterious things are happening here. I’m curious though, why did you set it to come in on step 21 when you only have 20 steps? Wouldn’t that prevent it from running? I’m missing something.
These are amazing. Nice work!
With Tinkerbell? I think Peter Pan and Rufus were into her? Good question. Sounds like I need to go watch it again.
Good point, haha!
Prompters need to add (21 years old:1.3) in the positive prompt and “child, childlike” in the negative prompt. They also need to judge better whether the content the AI produces is too young looking.
If you make something and think “is that too young?” Just assume it is and regenerate with the above tips. 21 is a good starting point because AI doesn’t seem to be completely accurate with ages yet.
Let me know what you find and if it’s useful! Cheers.
I thought it was an arm morphing into a Dyson. Gotta vacuum the deck, ya know?
Have you looked at this LoRa managing extension? I saw it mentioned on the regional prompt GitHub readme.
This extension summary:
By associating LoRA’s insertion position in the prompt with “AND” syntax, LoRA’s scope of influence is limited to a specific subprompt.
While I generally agree, there is some “artistry” in making prompts that work and figuring out all of the tricks to get better results. My own prompts have gotten a lot more interesting with custom checkpoint merging and dynamic and region prompting; these all took time to learn. I think posting the prompt/sources should be optional and people should request it if they want it, perhaps in a private message.
I understand that “AI prompter” is becoming a job for some people at some companies and I can now start to see why. As you try to generate more realistic and interesting images, you have to know more about how stable diffusion and the many extensions work. It goes pretty deep—I feel like I am only scratching the surface.
Nice work! Excited to see more of your creations.