Jump to content

AI illustrations of DOAXVV chara.


Recommended Posts

Posted (edited)

Did you make game UI lora?

I would just use screenshot and inpainting the characters.

 

 

 

00208_.png

Owner-kun, you gave me the best birthday present.

Edited by huehuehue9001
Posted (edited)
5 hours ago, huehuehue9001 said:

Did you make game UI lora?

I would just use screenshot and inpainting the characters.

 

 

 

00208_.png

Owner-kun, you gave me the best birthday present.

I made Mod to delete Character and delete background and delete foreground in Game. and I got background screenshot and foreground screenshot. Then I used [LayerDiffuse] in Sitable Diffusion. this way is not clear.

So your way is best! I will try to use inpainting. Thank you.

011.png

 

012.jpg

 

1.jpg

Edited by 5250
Posted (edited)

Still I can't get Azusa......

 

Generated same prompt used wildcards.

 

00154-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00158-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00159-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00160-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00166-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00167-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00168-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00169-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00171-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00176-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00178-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00179-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00180-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00181-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00191-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00193-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00195-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00198-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00199-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00202-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00203-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

00209-novaAsianXL_illustriousV70_DPM++ 2M SDE.jpeg

Edited by 5250
Posted (edited)

anime3dxl + doaxvv lora. 1MP t2i then upscaled to 1440p

92286_00001_.png

 

 

Loaded image into Qwen image edit 2509. Upscaled to 4k. denoise 0.4.

Without any character lora, qwen really have that same face look.

The background is good, the depth of field is smooth.

Upscaling to 4k with anime3dxl is not good.

The background is all grainy.

ComfyUI_00355_.png

Edited by huehuehue9001
Posted (edited)

bacon? beef jerky?

 

 

 

inpainting_00336_.thumb.png.93ad087b4730b75253a86b074f56f141.png

It's not her birthday.

Just trying out stuff.

so it's anime3dxl + lora > qwen upscale> inpainting back with anime3dxl + lora

maybe i'll try z image upscale.

 

 

Here is some testing.

 

anime3dxl 4k upscale. (2 minutes to gen)

Spoiler

anime3dxl4kupscale.thumb.png.1af1841bd69d8e6e6d802f2313261b0b.png

 

 

flux2 4b (9 minutes)

Spoiler

flux24b.thumb.png.72a82f784a935d28fba2b406cdccd112.png

 

 

z image. (1 minute)

Spoiler

zimage.thumb.png.8326126ee9fd08854960b8df37e1b972.png

 

 

base upscale (base image is 1344x768, then upscaled to 2528x1440)

this step is because 1MP is too low res to get a good face.

Spoiler

baseupscaled.thumb.png.239c603620e2837d37387efadf1ee5ea.png

 

 

qwen took 4 minutes i think.

Spoiler

qwen.thumb.png.9963af96f32a76667d4d4db18b0ed770.png

 

 

anime3dxl is grainy.

flux2 4b looks ok but it doesn't look 4K.

zimage is blurry and soft.

qwen looks 4K but the face is changed, nipples and cunny is baloney. so you have to fix it.

Edited by huehuehue9001
Posted (edited)
21 hours ago, huehuehue9001 said:

bacon? beef jerky?

 

 

 

inpainting_00336_.thumb.png.93ad087b4730b75253a86b074f56f141.png

It's not her birthday.

Just trying out stuff.

so it's anime3dxl + lora > qwen upscale> inpainting back with anime3dxl + lora

maybe i'll try z image upscale.

 

 

Here is some testing.

 

anime3dxl 4k upscale. (2 minutes to gen)

  Reveal hidden contents

anime3dxl4kupscale.thumb.png.1af1841bd69d8e6e6d802f2313261b0b.png

 

 

flux2 4b (9 minutes)

  Reveal hidden contents

flux24b.thumb.png.72a82f784a935d28fba2b406cdccd112.png

 

 

z image. (1 minute)

  Reveal hidden contents

zimage.thumb.png.8326126ee9fd08854960b8df37e1b972.png

 

 

base upscale (base image is 1344x768, then upscaled to 2528x1440)

this step is because 1MP is too low res to get a good face.

  Reveal hidden contents

baseupscaled.thumb.png.239c603620e2837d37387efadf1ee5ea.png

 

 

qwen took 4 minutes i think.

  Reveal hidden contents

qwen.thumb.png.9963af96f32a76667d4d4db18b0ed770.png

 

 

anime3dxl is grainy.

flux2 4b looks ok but it doesn't look 4K.

zimage is blurry and soft.

qwen looks 4K but the face is changed, nipples and cunny is baloney. so you have to fix it.

I tried to use Nova anime3dxl and others check point on Stable Diffusion Forge.

I don't use upscaler, because it slow down the generation speed. I use only face detailer.

So to make each pic need about 17 seconds. 

Since the resolution is reduced when the image is animated, I felt there was no need to upscale it.

So I made 1200-1600 dot pic on Forge.(Non upscale) then This pic is down scale (480-640) on ConfyUI, Then Upscale to 960-1280.


I'm also trying out a lot of different things.

 

novaAnimeXL_ilV160

00017-nova3DCGXL_ilV80_DPM++ 2M.jpeg

nova3DCGXL_ilV80

00013-novaAnimeXL_ilV160_DPM++ 2M.jpeg

novaOrangeXL_exV08

00021-novaOrangeXL_exV08_DPM++ 2M.jpeg

novaAsianXL_illustriousV70

00025-novaAsianXL_illustriousV70_DPM++ 2M.jpeg

Edited by 5250
Posted (edited)

the nova anime looks closest to game.

you can also try uncanny valley checkpoint on civitai.

looks good for sayuri. probably because her realistic design.

 

I also found the doaxvv lora is making the background grainy when upscaling.

So I tried to go as lowest as possible. That is 0.4 strength. Going lower the face is not the same as game.

Turning lora off works too if going with low denoise. You can always inpaint or adetailer later.

Edited by huehuehue9001
Posted
6 minutes ago, huehuehue9001 said:

I think the doaxvv lora is making the background grainy.

try lora at 0.4 strength.

Oh! Thank you for your advice. I will try!

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
  • Recently Browsing   0 members

    • No registered users viewing this page.
×
×
  • Create New...