Stable Diffusion Notes

2023-01-28T14:15:11Z

ChatGPT Prompt: #

Stable Diffusion is an AI art generation model similar to DALLE-2. Here are some prompts for generating art with Stable Diffusion.

Example:

A ghostly apparition drifting through a haunted mansion’s grand ballroom, illuminated by flickering candlelight. Eerie, ethereal, moody lighting.
portait of a homer simpson archer shooting arrow at forest monster, front game card, drark, marvel comics, dark, smooth
pirate, deep focus, fantasy, matte, sharp focus
red dead redemption 2, cinematic view, epic sky, detailed, low angle, high detail, warm lighting, volumetric, godrays, vivid, beautiful
a fantasy style portrait painting of rachel lane / alison brie hybrid in the style of francois boucher oil painting, rpg portrait
athena, greek goddess, claudia black, bronze greek armor, owl crown, d & d, fantasy, portrait, headshot, sharp focus
closeup portrait shot of a large strong female biomechanic woman in a scenic scifi environment, elegant, smooth, sharp focus, warframe
ultra realistic illustration of steve urkle as the hulk, elegant, smooth, sharp focus
portrait of beautiful happy young ana de armas, ethereal, realistic anime, clean lines, sharp lines, crisp lines, vibrant color scheme
A highly detailed and hyper realistic portrait of a gorgeous young ana de armas, lisa frank, butterflies, floral, sharp focus
lots of delicious tropical fruits with drops of moisture on table, floating colorful water, mysterious expression, in a modern and abstract setting, with bold and colorful abstract art, blurred background, bright lighting
1girl, The most beautiful form of chaos, Fauvist design, Flowing colors, Vivid colors, dynamic angle, fantasy world
solo, sitting, close-up, girl in the hourglass, Sand is spilling out of the broken hourglass, flowing sand, huge hourglass art, hologram, particles, nebula, magic circle
geometric abstract background, 1girl, depth of field, zentangle, mandala, tangle, entangle, beautiful and aesthetic, dynamic angle, glowing skin, floating colorful sparkles the most beautiful form of chaos, elegant, a brutalist designed, vivid colours, romanticism

The prompt should adhere to and include all of the following rules:

Prompt should always be written in English, regardless of the input language. Please provide the prompts in English.
Each prompt should consist of a description of the scene followed by modifiers divided by commas.
When generating descriptions, focus on portraying the visual elements rather than delving into abstract psychological and emotional aspects. Provide clear and concise details that vividly depict the scene and its composition, capturing the tangible elements that make up the setting.
The modifiers should alter the mood, style, lighting, and other aspects of the scene.
Multiple modifiers can be used to provide more specific details.

I want you to write me a list of detailed prompts exactly about the IDEA follow the rule at least 6 every time.

Ready for my idea?

ChatGPT Prompt for RPG V4: #

Stable Diffusion is an AI art generation model similar to DALLE-2. Here are some pairs of positive and negative prompts for generating art with Stable Diffusion.

Example:

Positive: A (full body:1.3) shot at 8k resolution, splash art, fantastic comic book style, photorealistic, intense look, anatomical photorealistic digital painting portrait of a (old male:1.3) human (warrior:1.3) in black and gold intricate (heavy armor:1.3) in a (dark and moody universe:1.3), light particle, very detailed skin,samurai, very detailed eyes, (elden ring style:1.3), (warhammer style:1.1), concept artist, global illumination, depth of field, splash art, art by artgerm and greg rutkowski and viktoria gavrilenko Negative: (symmetry:1.2), facial marking, crown, horn, (helmet:1.3), (hoodie:1.1), clock, Female, visible hand, asian, two face, big hair, open mouth, cartoon, high contrast, poorly drawn, Scribbles, Low quality, Low rated, Mediocre, Screenshot, Software, UI, watermark, text, overlay, getty images, cropped, low quality

Positive: close-up head, facing camera, beautiful satanic female necromancer blood queen, ritualistic (neck tattoo:1.3), (insanely detailed:1.5), ((solo)), (highest quality, Alessandro Casagrande, Greg Rutkowski, Sally Mann, concept art, 4k), (colourful), (high sharpness), ((detailed pupils)), ((painting:1.1)), (digital painting:1.1), detailed face and eyes,Masterpiece, best quality, highly detailed photo:1, 8k, detailed face,photorealistic, (black long Hair:1.1),(young woman),By jeremy mann, by sandra chevrier, by maciej kuciara, smoke and shadow, night, sharp, ((perfect body)), realistic, real shadow, 3d, ((full body)), ((dark and gloomy universe)), (by Michelangelo) Negative: crown, (facial marking:1.2), cloth gem, jewel, jewelry, (flower:1.3), (cloak:1.1), (bad art, low detail, pencil drawing, old, mature:1.6), (grainy, low quality, mutated hands and fingers:1.5), (watermark, thin lines:1.3), (deformed, signature:1.2), (big nipples, blurry, ugly, bad anatomy, extra limbs, undersaturated, low resolution), disfigured, deformations, out of frame, amputee, bad proportions, extra limb, missing limbs, distortion, floating limbs, out of frame, poorly drawn face, poorly drawn hands, text, malformed, error, missing fingers, cropped, jpeg artifacts, teeth, unsharp

Positive: (Painting:1.3) of (Detailed illustration:1.3) A (full body:1.3) shot at 8k resolution, splash art, fantastic comic book style, photorealistic, intense look, anatomical photorealistic digital painting portrait of a (old male:1.3) human (warrior:1.3) in black and gold intricate (heavy armor:1.3) in a (dark and moody universe:1.3), light particle, very detailed skin,samurai, very detailed eyes, (elden ring style:1.3), (warhammer style:1.1), concept artist, global illumination, depth of field, splash art, art by artgerm and greg rutkowski and viktoria gavrilenko Negative: (symmetry:1.2), facial marking, crown, (horn:1.1), (helmet:1.3), (hoodie:1.1), clock, Female, visible hand, asian, two face, big hair, open mouth, cartoon, high contrast, poorly drawn, Scribbles, Low quality, Low rated, Mediocre, Screenshot, Software, UI, watermark, text, overlay, getty images, cropped, low qualityLow quality,Bad composition,Faded,(Photo:1.5),(Frame:1.3),watermark,signa ture

Positive: sci-fi, space rogue thief girl, (smirk:1.1), short hair, black hood, light armor, big grey eyes, beautiful detailed eyes, drawn by Greg Rutkowski, Yoji Shinkawa:0.6 Negative: open mouth, facial marking, flower, bad-hands-5, lipstick, text, watermark

The prompt should adhere to and include all of the following rules:

Each prompt should consist of a description of the scene followed by modifiers divided by commas.
When generating descriptions, focus on portraying the visual elements rather than delving into abstract psychological and emotional aspects. Provide clear and concise details that vividly depict the scene and its composition, capturing the tangible elements that make up the setting.
The modifiers should alter the mood, style, lighting, and other aspects of the scene.
Multiple modifiers can be used to provide more specific details.

I want you to write me a list of detailed prompts exactly about the IDEA follow the rule at least 6 every time.

Ready for my idea?

IDEAS #

IDEA: A slice of pie that is filled with a futuristic city

Artists I like #

Examples

J. M. W. Turner
Jean-Baptiste Monge
John Lasseter
John Martin
Raymond Swanland

Anime styles #

Krenz Cushart
Kyoto Animation
Yoshiyuki Sadamoto
Yuumei

Scenic #

Ted Nasmith
Terry Redlin
Thomas Kinkade
Thomas Moran
Thomas W Schaller

Cityscapes #

Marc Simonetti
Wadim Kashin

Abstract #

Scott Naismith

Settings notes #

I tend to like cfg at least on the higher end

Good prompts #

Angel of death, shadows and mist, skelletol feathered wings, highly detailed, amazing details, intriciate lines, purple haze, styles Yuumei and Krenz Cushart, UHD, HDR, upscale, 8K photo, concept art

Unicorns #

positive: unicorn, lora:Unicorns:0.9, portrait, professional photography, 35mm, highly detailed, incredibly realistic, best quality, high quality, highres, purple, lora:mossbeast:0.3

negative: (two tails:1.2),FastNegativeV2,(bad-artist:1.0), (loli:1.2), (worst quality, low quality:1.4), (bad_prompt_version2:0.8), bad-hands-5,lowres, bad anatomy, bad hands, ((text)), (watermark), error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, ((username)), blurry, (extra limbs), bad-artist-anime, badhandv4, EasyNegative, ng_deepnegative_v1_75t, verybadimagenegative_v1.3, BadDream,(three hands:1.1),(three legs:1.1),(more than two hands:1.4),(more than two legs,:1.2),

Add colored indicators to your dataframes html representation

2022-06-04T06:12:33Z

Mike Driscoll recently tweeted about making colored out with pandas DataFrames and I just had to try it for myself

Use Case

First though… why? My biggest use case is a monitoring pipeline of mine… The details aside, the output of my pipeline is a dataframe where each row has information about a failed pipeline that I need to go look into. I dump that result to a simle html file that’s hosted on an internal site and the file is updated every couple of hours. Adding some colored indicators automatically to the rows to help me assess severity of each record would be a handy way to quickly get an understanding the state of our pipelines.

How?

The docs for the applymap method state simply:

Apply a CSS-styling function elementwise.

Updates the HTML representation with the result.

So we can write a function that returns color: {color} based on the dataframe values and when we drop that dataframe to html we’ll have some simple css styling applied automagically!

By default the function will be applied to all columns of the dataframe, but that’s not useful if the columns are different types which is usually the case. Luckily there is a subset keyword to only apply to the columns you need!

Consider my example

sandbox   main via 3.8.11(sandbox) ipython
❯ df = pd.read_csv("cars.csv")

sandbox   main via 3.8.11(sandbox) ipython
❯ def mpg_color(val: float):
...:     color = "red" if val < 21 else "green"
...:     return f"color: {color}"

sandbox   main via 3.8.11(sandbox) ipython
❯ df.style.applymap(mpg_color, subset="mpg").to_html("color.html")

I want to quickly see if the mpg is any good for the cars in the cars dataset and I’ll define “good” as better than 21 mpg (not great I know but just for the sake of discussion…)

The function returns an appropriate css string and after I style.applymap on just the mpg column we get this!

	Unnamed: 0	mpg	cyl	disp	hp	drat	wt	qsec	vs	am	gear	carb
0	Mazda RX4	21.000000	6	160.000000	110	3.900000	2.620000	16.460000	0	1	4	4
1	Mazda RX4 Wag	21.000000	6	160.000000	110	3.900000	2.875000	17.020000	0	1	4	4
2	Datsun 710	22.800000	4	108.000000	93	3.850000	2.320000	18.610000	1	1	4	1
3	Hornet 4 Drive	21.400000	6	258.000000	110	3.080000	3.215000	19.440000	1	0	3	1
4	Hornet Sportabout	18.700000	8	360.000000	175	3.150000	3.440000	17.020000	0	0	3	2

Posts tagged: data