[381 / 136 / 75]
Classy Cynthia edition
>what's everyone's using
https://novelai.net/image
>How to use
enter Danbooru tags & read guide
https://docs.novelai.net/
>I can't get my character to like themselves
Use key features/tags that the characters have to guide the ai Ex:
>Misty (pokemon), yellow shirt, suspenders, orange hair,shorts. or even
>Hilda (pokemon), high ponytail, denim shorts, brown hair, black vest. or for chicken
>Selene (pokemon), tied shirt, loose clothes,green shorts, swept bangs, red beanie
>local Install for Retards
1. Install 1Click Stable Diffusion https://github.com/cmdr2/stable-diffusion-ui
2. Add Waifu Model https://huggingface.co/hakurei/waifu-diffusion-v1-3/resolve/main/wd-v1-3-float16.ckpt & move to the \models\stable-diffusion folder
3. Add Novel Model magnet:?xt=urn:btih:5bde442da86265b670a3e5ea3163afad2c6f8ecc you only need the files in the "animefull-final-pruned" folder. Rename for clarity the 2 files and move to the \models\stable-diffusion folder
Select a model in the UI drop down.
Samplers give different details, start with Euler.
Steps is how many iterations, start with 28.
Guidance is how strict to the prompt, start with 11.
Negative Prompt Baseline: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name
Prompt Baseline: masterpiece, best quality. YOUR IDEA GOES HERE
>Additional tips
- Almost all characters are possible if you describe them in tags, in addition to using their name in the prompt. Look on Danbooru and copy the tags they use there (check multiple images) in your prompt.
- You are not restricted to using tags, the ai will also recognize your own made tags, just not as well as Danbooru's tags. Use emphasizing and deemphasizing to steer the ai the right direction.
- Generation pics in another artstyle is possible. Aside from mentioning the artist, describe their style.
>what's everyone's using
https://novelai.net/image
>How to use
enter Danbooru tags & read guide
https://docs.novelai.net/
>I can't get my character to like themselves
Use key features/tags that the characters have to guide the ai Ex:
>Misty (pokemon), yellow shirt, suspenders, orange hair,shorts. or even
>Hilda (pokemon), high ponytail, denim shorts, brown hair, black vest. or for chicken
>Selene (pokemon), tied shirt, loose clothes,green shorts, swept bangs, red beanie
>local Install for Retards
1. Install 1Click Stable Diffusion https://github.com/cmdr2/stable-diffusion-ui
2. Add Waifu Model https://huggingface.co/hakurei/waifu-diffusion-v1-3/resolve/main/wd-v1-3-float16.ckpt & move to the \models\stable-diffusion folder
3. Add Novel Model magnet:?xt=urn:btih:5bde442da86265b670a3e5ea3163afad2c6f8ecc you only need the files in the "animefull-final-pruned" folder. Rename for clarity the 2 files and move to the \models\stable-diffusion folder
Select a model in the UI drop down.
Samplers give different details, start with Euler.
Steps is how many iterations, start with 28.
Guidance is how strict to the prompt, start with 11.
Negative Prompt Baseline: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name
Prompt Baseline: masterpiece, best quality. YOUR IDEA GOES HERE
>Additional tips
- Almost all characters are possible if you describe them in tags, in addition to using their name in the prompt. Look on Danbooru and copy the tags they use there (check multiple images) in your prompt.
- You are not restricted to using tags, the ai will also recognize your own made tags, just not as well as Danbooru's tags. Use emphasizing and deemphasizing to steer the ai the right direction.
- Generation pics in another artstyle is possible. Aside from mentioning the artist, describe their style.
