Comments

Yeah. This seems to be great to have in any good local park.

To anyone who want the process:
1.generate a tree
2.use controlnet canny/lineart keep all branches in same shape/place.
3.just generate 4 images with 4 seasons with that controlnet.
4.PS them together.

{Shameimaru Aya(touhou)}, full body, {raise magic}, falling down, beautiful girl, Elden ring painting style, by rolua n,by yoneyama mai, oil painting, sketch painting, {limited color sketch}, masterpiece, photo background, film still, by stu_dts,by archlich

msn666 said:

{Shameimaru Aya(touhou)}, full body, {raise magic}, falling down, beautiful girl, Elden ring painting style, by rolua n,by yoneyama mai, oil painting, sketch painting, {limited color sketch}, masterpiece, photo background, film still, by stu_dts,by archlich

Feel free to edit it via "Add metadata", lol. Boorus are catalogue websites, the model doesn't work if you don't tag.

this is gona be a good desktop wallpaper

It might not look best in the contest. But I think it fits the theme most.

b74 said:

It might not look best in the contest. But I think it fits the theme most.

I think this is easily the best of the submissions, it's incredibly sad to see it get downvoted like this :,(

Before: post #4263
After:

i just love it when my checkpoints get mad after prompting "getting-totally-ignored" D

Stapfschuh said:

i just love it when my checkpoints get mad after prompting "getting-totally-ignored" D

Probably because the checkpoints are trained on danbooru tags, not the prompts you use

sulph said:

Probably because the checkpoints are trained on danbooru tags, not the prompts you use

nah... every prompt i ever created is working like a charme on every checkpoint. "mad" is just meant i a way that those characters basically always run away or do other dumb stuff every time i prompt "getting-totally-ignored". it has nothing to do with danboorus tags

Chapa Chapa ~

Dubi Dubi

damn i want to be able to do this

sulph said:

damn i want to be able to do this

Background Creation:
- Place objects in Unity to create the background and capture the screen.
- Use LCM for real-time previews.

Vending Machine Photo:
- Once angles are decided, take a photo of the vending machine.
- Extract only the line art information from the photo, simplify it, adjust scale and placement, and add objects.

Character Movement and Video:
- Determine character movements and record yourself acting in front of a smartphone camera.
- Use object detection nodes to adjust proportions (similar to the method used with the snow Miku-chan).
- Extract only posture information.
- Use Openpose for v2v (assisted by prompts for each frame, including expression changes).

Illustration:
- Composite background and character using Shoost.
- Create light sources in Krita for rendering.

Retouching and Upscaling:
- Retouch in Krita for final touches.
- Finally, upscale the image.

Enferlain said:

Background Creation:
- Place objects in Unity to create the background and capture the screen.
- Use LCM for real-time previews.

Vending Machine Photo:
- Once angles are decided, take a photo of the vending machine.
- Extract only the line art information from the photo, simplify it, adjust scale and placement, and add objects.

Character Movement and Video:
- Determine character movements and record yourself acting in front of a smartphone camera.
- Use object detection nodes to adjust proportions (similar to the method used with the snow Miku-chan).
- Extract only posture information.
- Use Openpose for v2v (assisted by prompts for each frame, including expression changes).

Illustration:
- Composite background and character using Shoost.
- Create light sources in Krita for rendering.

Retouching and Upscaling:
- Retouch in Krita for final touches.
- Finally, upscale the image.

Nice translation.

500 uploads

MrBean said:

500 uploads

road to 1000?

This is cool, surprised the score is so low.

total animator death

bro the hentai boutta go SOOOOO CRAZY

i got defeated

how was this made? is it a img2img?

sulph said:

how was this made? is it a img2img?

No.

Here is the complete prompt for the base image. Then I just increased the resolution and improved the details.

"""
high quality,highres,
1girl,solo,(loli:0.6),(child:0.6),(flat chest:0.6),blonde hair,
maid,
(indoors,cafe:0.7),
Negative prompt: (worst quality, low quality:1.3),monochrome,zombie,(interlocked fingers),blurry,extra hands,extra legs,(wide hips:1.2),(extra fingers, deformed hands, polydactyl:1.1),three legs,(huge ass:1.2),(medium breasts,small breasts:1.2),(thick thighs:1.2),lying,on back,
Steps: 25, Sampler: DPM++ 2M Karras, CFG scale: 7, Seed: 457388931, Size: 768x512, Model hash: e4feb0e534, Model: haiku_v10, VAE hash: 11b79e77c4, VAE: a_perfect_color_mpaffl.safetensors, Clip skip: 2, Version: v1.8.0
"""