Stable Diffusion - photo to anime prompt

https://stablediffusion.cdcruz.com/

Models

AUTOMATIC1111 - Cheat Sheet

Attention/emphasis

https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Features#attentionemphasis

Using () in the prompt increases the model's attention to enclosed words, and [] decreases it. You can combine multiple modifiers:

Cheat sheet:

a (word) - increase attention to word by a factor of 1.1
a ((word)) - increase attention to word by a factor of 1.21 (= 1.1 * 1.1)
a [word] - decrease attention to word by a factor of 1.1
a (word:1.5) - increase attention to word by a factor of 1.5
a (word:0.25) - decrease attention to word by a factor of 4 (= 1 / 0.25)
a \(word\) - use literal () characters in prompt

With (), a weight can be specified like this: (text:1.4). If the weight is not specified, it is assumed to be 1.1. Specifying weight only works with () not with [].

If you want to use any of the literal ()[] characters in the prompt, use the backslash to escape them: anime_\(character\).

On 2022-09-29, a new implementation was added that supports escape characters and numerical weights. A downside of the new implementation is that the old one was not perfect and sometimes ate characters: "a (((farm))), daytime", for example, would become "a farm daytime" without the comma. This behavior is not shared by the new implementation which preserves all text correctly, and this means that your saved seeds may produce different pictures. For now, there is an option in settings to use the old implementation.

NAI uses my implementation from before 2022-09-29, except they have 1.05 as the multiplier and use {} instead of (). So the conversion applies:

their {word} = our (word:1.05)
their {{word}} = our (word:1.1025)
their [word] = our (word:0.952) (0.952 = 1/1.05)
their [[word]] = our (word:0.907) (0.907 = 1/1.05/1.05)

ใช้ Waifu Diffusion

img2img

Prompt

Girl = ผู้หญิง (ยืนพื้นด้วย prompt นี้)
Photo = เพิ่มความสมจริง
beautiful =

หรือใส่อะไรก็ใส่คำพื้นฐานทั่วไป

Monochome or black and white - massive influence - will make everything black and white
Sepia - mild influence - will give a sepia colour palette.
Color/ colour - weak influence - Not really required for more images as they are usually in colour.
Colourful/ colorful - mild influence - Will add more variety of colour in the image.
Traditional Art - mild influence - a general art prompt with varying styles and detail.
Painting - strong influence - will add paintery brush strokes to image.
Ink art - mild influence - Basically makes black and white drawings.
Chalk art - mild influence - Sometimes adds a chalk effect to image, sometimes adds random blackboard scribbles to background.
Oil painting - weak influence - seems to be less powerful than simply using "painting".
Watercolour/watercolor - strong influence - adds a similar effect as "painting" but does distinctly look more watercolour-like.
Drawing - mild influence - Will add a more pencil-like style to the image. But seems more digital pencil than real pencil.
Photo/photograph - strong influence - will make the image much more realistic, but in Waifu Diffusion it will maintain anime characteristics and skin will be smooth.
Canon 50D (or other camera types) - mild/ strong influence - will make the image more realistic.
Cinematic lighting - mild/strong influence - will add more dramatic lighting and usually a point light in the scene. Also darker scenes and backlit scenes.
God Rays - mild/strong influence - will add a strong sun light that will usually shine on one side of a persons head/ hair. Can also add rays of light but less likely.
Cell Shading - strong influence - a detailed anime style, most similar to visual novel characters.
Anime - strong influence - Anime
Waifu - Despite the name of the ai, doesn't seem to change much style wise.
Key Visual - strong influence - A detailed anime style while keeping the anime characteristics or big eyes, etc.
Hentai - mild/strong influence - This prompt varies between realistic and anime style depending on other prompts and will also obviously make the image more lewd.
Artstation - strong influence - A variety of artstyles, usually more professional looking.
By Toei Animation - strong influence - A better anime prompt for more detailed anime.
By Studio Ghibli - strong influence - A better anime prompt for simple anime characters and classic Ghibli backgrounds.
In the style of Mappa - mild influence - Another anime style.
By Kyoto Animation - mild influence - Anime
In the style of Cloverworks - mild influence - Anime
Model - mild influence - Helps a person look more "perfect", they will also usually look directly at the camera.
Instagram - mild influence - Characters have a much wider range of poses and camera angles
vtuber - strong influence - will generate anime characters mainly in the style of vtubers.
Snapchat - weak influence - Similar to "Instagram" but also produces more selfie-like images.
Professional - weak influence - looks more professional shot and has more background variety butthe background is usually out of focus.
Ponytail/pigtails/braids/(Various hairstyles) - strong influence - will change hairstyle a lot.

Negative Prompt

deformed, blurry, bad anatomy, disfigured, poorly drawn face, mutation, mutated, extra_limb, ugly, poorly drawn hands, two heads,child, children, kid, gross, mutilated, disgusting, horrible, scary, evil, old, conjoined, morphed, text, error, glitch, lowres, missing digits, watermark, signature, jpeg artifacts, low quality

ค่าที่จำเป็น

Width, Height ตั้งให้ใกล้เคียงต้นฉบับ

CFG Scale: 12

Denoise: 0.5 (ยิ่งน้อยยิ่งเหมือนต้นฉบับ ค่านี้ปรับไปปรับมาระหว่าง 0.3-0.5 กำลังดี)