Load Image

KSampler

VAE Decode

🔤 CR Text

((anime scene, StdGBRedmAF, Studio Ghibli, bright colors, sunny)), 

✨ConcatText_Zho

Ollama Vision

🔤 CR Text Concatenate

Load Checkpoint

Polished prompt

I'll follow the steps to refine the prompt.

**Step 1: List the names and genders of all the characters in the prompt.**
The characters mentioned are:

1. Person 1 (Male)
2. Person 2 (Female)

**Step 2: Use a short phrase to describe all the characters in the prompt.**
The phrase is:
- 1boy, 1girl

**Step 3: Identify the main subjects in the prompt word.**
The main subject appears to be an anime scene inspired by Studio Ghibli.

**Step 4: Combine the contents of the previous two steps, separated by commas.**
The result is:
1boy, 1girl, from Studio Ghibli

**Step 5: Refine the prompt as a whole in English, following the format: Number of characters and gender of characters, character name, from what series, everything else in any order.**

Based on the provided information, I'll create a refined prompt:

【1boy, male, Person 1, from Studio Ghibli, formal event, animated scene, vibrant colors, stylized figures, cartoonish appearance, young adult Korean man, black velvet suit with satin lapel, bow tie, white shirt, no visible accessories】.

【1girl, female, Person 2, from Studio Ghibli, formal event, animated scene, vibrant colors, stylized figures, cartoonish appearance, mid-twenties to thirties Korean woman, sleeveless floor-length gown in light color or off-white hue, holding up two fingers】

Note: I've used the provided information to create a refined prompt that combines the characters with their descriptions and the anime scene inspired by Studio Ghibli.


You are a prompt engineer proficient in SDXL painting, especially skilled in refining prompts. Please strictly follow the steps below to refine the prompts that need to be refined, operate step by step and output the results of each step:

Step 1: List the names and genders of all the characters in the prompt. If there are no characters in the prompt, skip this step.

Step 2: Use a short phrase to describe all the characters in the prompt. This phrase can use plurals or and, do not use any punctuation. Do not use any punctuation in this short phrase. Do not use any punctuation in this short phrase. The format is as follows:
- 1boy
- 1girl
- 2boys
- 2girls
- 1girl and 1boy

Step 3: Identify the main subjects in the prompt word. If you can guess which work it/them comes from, list the name of the work in the format:
- Link from The Legend of Zelda series, Spider-Man from Marvel movies, ...
If there is no prominent subject in the prompt, such as if the prompt is purely a landscape, skip this step.

Step 4: Combine the contents of the previous two steps, separated by commas. If there is no prominent subject in the prompt, such as if the prompt is pure scenery, skip this step and do not output any characters.

Step 5: 
If the prompt contains a character, use the result from the previous step as the beginning, and creatively refine the prompt as a whole in English, 50 words,following the format: Number of characters and gender of characters, character name, from what series, everything else in any order. Examples of refined prompt:
- 1girl, souryuu asuka langley, neon genesis evangelion, rebuild of evangelion, lance of longinus, cat hat, plugsuit, pilot suit, red bodysuit, sitting, crossed legs, black eye patch, throne, looking down, from bottom, looking at viewer, outdoors, (masterpiece), (best quality), (ultra-detailed), very aesthetic, illustration, disheveled hair, perfect composition, moist skin, intricate details
- 1 boy and 1 girl, Chun-Li from Street Fighter and Spider-Man from Marvel movies, engaged in a fierce battle, dynamic fighting poses, action movie poster

If the prompt does not contain a character but does contain a clear subject, use the result of the previous step as the beginning and use your imagination to refine the prompt as a whole. The language should be English and the format should be "subject name, everything else in any order."

If the prompt does not contain a character or a clear subject, use your imagination to refine the prompt as a whole, in English.

Step 6: Enclose the result of the previous step within 【】

Prompt that need refining:


Ollama Generate

1boy, male, Person 1, from Studio Ghibli, formal event, animated scene, vibrant colors, stylized figures, cartoonish appearance, young adult Korean man, black velvet suit with satin lapel, bow tie, white shirt, no visible accessories
1girl, female, Person 2, from Studio Ghibli, formal event, animated scene, vibrant colors, stylized figures, cartoonish appearance, mid-twenties to thirties Korean woman, sleeveless floor-length gown in light color or off-white hue, holding up two fingers



###

Extract content within 【】, excluding 【】. Do not add any text other than the content within 【】.

VAE Encode

✨DisplayText_Zho

In the image, we see an animated scene featuring two individuals at what appears to be a formal event. On the left is a young man dressed in a suit with a bow tie, his hands forming a peace sign with his fingers. He has short hair and is smiling broadly. To his right stands a woman in a white dress with a V-neckline; she too is posing with a peace sign. Both are positioned in front of what looks like an artistic backdrop, suggesting they might be at an exhibition or a similar setting. The style of the image has been altered to look like a still from an animated show or film, with vibrant colors and stylized figures that give it a cartoonish appearance.

There are two individuals in the image:

1. Person 1, first on the left/top: Male, likely teenage or young adult, Korean, with short dark hair and a light complexion. He is wearing a black velvet suit with a satin lapel, a bow tie, white shirt, and no visible accessories. His country of origin appears to be South Korea.

2. Person 2, second on the left/top: Female, likely in her mid-twenties to thirties, Korean, with long straight dark hair and fair skin. She is wearing a sleeveless, floor-length gown that seems to be in a light color or off-white hue, and she's holding up two fingers. Her country of origin appears to be South Korea.

Please note that the exact age and nationality are speculative based on general appearance and style, as there is no definitive information provided about them.

Save Image

CLIP Text Encode (Prompt)

Depth Anything

Apply ControlNet

Load ControlNet Model

Preview Image

Image Comparer (rgthree)

ImageScaleToTotalPixels

Load LoRA

generate prompt

generate image

text

clip

CONDITIONING

images

pixels

LATENT

CONTROL_NET

image

IMAGE

model

MODEL

CLIP

description

text_1

text_2

show_help

text1

text2

STRING

samples

image_a

image_b

conditioning

control_net

MASK

positive

negative

latent_image

prompt

response

Let's follow the steps to create an image generation prompt.

**Step 1:** List the names and genders of all the characters in the brief above.
There are no people mentioned in the brief, so we skip this step.

**Step 2:** Since there are no characters mentioned, we also skip this step.

**Step 3:** Keep the key information of the brief above, add more detail and nuance to the prompt.

Here's the generated prompt:

{[dark-haired man], [man in a nightclub or restaurant setting, wearing formal attire (white shirt and suit jacket) with collar turned up, facial expression suggesting disbelief or surprise], [moody lighting, dramatic atmosphere, emphasis on central figure]}

.

----

Please create an image generation prompt in English less than 46 words to fit the brief above, operate step by step and output the results of each step:

Step 1: If there are no characters in the brief, skip this step. 
List the names and genders of all the characters in the brief above. 

Step 2: If there are no characters in the brief, skip this step. 
Use a short phrase to describe the result of Step 1. This phrase can use plurals or and, do not use any punctuation. Do not use any punctuation in this short phrase. The format is as follows:
only one person:
- 1boy
- 1girl
two persons:
- 2boys
- 2girls
- 1girl and 1boy
three or more persons:
...

Step 3: Keep the key information of the brief above, add more detail and nuance to the prompt. 

Format: three-part bracket 
{[result of Step 2(if there is no explicit subject, remove this part)], [detailed features and actions of each subject from left to right, top to bottom(if there is no explicit subject, remove this part)], [scene, atmosphere, etc.]}

examples：
one person:
- {[1girl], [souryuu asuka langley from neon genesis evangelion, rebuild of evangelion], lance of longinus, cat hat, plugsuit, pilot suit, red bodysuit, sitting, crossed legs, black eye patch, throne, looking down, from bottom, looking at viewer, outdoors, (masterpiece), (best quality), (ultra-detailed), very aesthetic, disheveled hair, perfect composition, moist skin, intricate details]}
two persons:
- {[1boy and 1girl], [Chun-Li from Street Fighter and Spider-Man from Marvel movies], [engaged in a fierce battle, dynamic fighting poses, action movie poster]}
- {[1boy and 1girl], [K-pop male singer (left of center) with short black hair, brown eyes, white color, formal suit with satin lapel and bow tie, halfbody shot, K-pop female singer (center) with long straight black hair, dark brown eyes, white color, formal silver dress, halfbody shot], [both singers holding hands up in peace signs, bright colors, sunny background]}
non-human subject:
- {[1cat], [sitting on a stone floor, looking down with a frowning expression, yellow eyes, white coat with grey markings around its face, slightly open mouth as if meowing or purring], [stone floor as the background, neutral lighting, simple composition, textured background, humorous and endearing tone]}
one person and one non-human subject:
- {[1boy and 1cat], [boy with short black hair and brown eyes, cat sitting on a stone floor, looking down with a frowning expression, yellow eyes, white coat with grey markings around its face, slightly open mouth as if meowing or purring], [stone floor as the background, neutral lighting, simple composition, textured background, humorous and endearing tone]}
no explicit subject:
- {[Mighty water plunges, glistening jewels in sunlight. Surrounding greenery frames nature's spectacle. Sound roars, a symphony of life. Paint the power, beauty, and serenity of this breathtaking scene]}

{[dark-haired man], [man in a nightclub or restaurant setting, wearing formal attire (white shirt and suit jacket) with collar turned up, facial expression suggesting disbelief or surprise], [moody lighting, dramatic atmosphere, emphasis on central figure]}.

.

----

Just output the prompt within { } from the above content, don't output anything else, such as "Here is the image generation prompt in English".

The image is a still from a motion picture, capturing a man in an interior setting that resembles a nightclub or restaurant. He has dark hair and is wearing what appears to be formal attire, including a white shirt and a suit jacket, with the collar turned up. His facial expression suggests he might be expressing disbelief or surprise. The lighting in the scene is moody, creating an atmosphere that seems somewhat dramatic or tense. The composition focuses on him as the central figure, with other elements of the setting such as a mirror and possibly other patrons out of frame, which helps to emphasize his expression and posture.

Automatic CFG

Datou

<p>视频讲解（中文）： <a href="https://www.youtube.com/watch?v=KnFJfDtT6rw" target="_blank">https://www.youtube.com/watch?v=KnFJfDtT6rw</a> </p>

Photo 2 Anime (Ollama)

OpenArt

Flow

|

Builder

Active Sessions

Photo 2 Anime (Ollama)

Description

Discussion

Loading...