Diffus
Inizia
modelli/MixTape /// Blues - v3.0 Soul Baked VAE

MixTape /// Blues - v3.0 Soul Baked VAE

Kate Thompson
|
10/23/2023
|
2:57:42 PM
| Discussion|
0
AI generated image using Stable Diffusion of a woman with dark hair wearing a red jacket and pink scarf, holding a wrapped gift, standing in front of a snowy cityscape.

Prompt Consigliati

(masterpiece, best quality:1.4)

(beautiful, perfect, delicate, detailed, intricate, aesthetic:1.2)

(masterpiece,best quality:1.4),(beautiful,aesthetic,perfect,delicate,intricate:1.2),(cute,adorable),(depth of field:1.2),(1girl,solo),colorful,vivid colors,perfect female form,glossy pink lips,expressive eyes,eyeshadow,eyeliner

Prompt Negativi Consigliati

EasyNegative,BadHands,BadArtist,BadArtistAnime,BadPrompt,(low quality, worst quality:1.4),(monochrome, grayscale, sketch:1.2)

EasyNegative,BadHands,BadArtist,BadArtistAnime,BadPrompt,BadImages,(low quality,worst quality:1.4),(monochrome,grayscale,sketch:1.2),(logo,signature,text,words,username,artist name,watermark),3d max,grotesque,desaturated,cartoon,halftone print,zombie,overexposure,bad anatomy,(loli:1.2),chibi,mask,(muscles,muscular,toned)

Parametri Consigliati

samplers

DPM++ SDE Karras

steps

40

cfg

8

clip skip

2

resolution

512x768

vae

VaeMse840000Pruned.ckpt (df3c506e51)

other models

mixtapeBlues_v30SoulBakedVAE (1429806246)

Parametri Consigliati per Alta Risoluzione

upscaler

4x-UltraSharp

upscale

2

steps

6

denoising strength

0.5

Punti Salienti della Versione

Soul version with baked VAE

Both image and music are windows to the deepest feelings, inviting us to explore the nuances of life through its different forms of expression.

Let's create a gallery full of inspiration! Post your masterpieces and let's fill civitai with imagination, creativity, expression and joy!

The Model MixTape Blus is similar to the MixTape Rock n' Roll, using the model DuckHaitenNiji in its base, but with a different mix. It's not very good with your hands, but it creates images with rich details and colors.

The Delta version is the most stylized. It creates very colorful images, with lots of detail and a more three-dimensional finish.

The Swamp version has more realistic proportions but still creates stylized, colorful and very detailed images. Features more facial expressions and more varied backgrounds.

The Soul version creates people with the most realistic proportions. Makes good facial expressions, lots of details. Create some very naughty scenes ;)

Recommends

Positive Prompt:

(masterpiece, best quality:1.4), (beautiful, perfect, delicate, detailed, intricate, aesthetic:1.2), ...

Negative Prompt:

EasyNegative, BadHands, BadArtist, BadArtistAnime, BadPrompt, (low quality, worst quality:1.4), (monochrome, grayscale, sketch:1.2), (logo, signature, text, words, username, artist name, watermark), (loli:1.2), ...

Embeddings (Textual Inversion): EasyNegative, BadHands, BadArtist, BadArtistAnime, BadPrompt

Sampling method: DPM++ SDE Karras

Sampling steps: 30 ~ 50

Hires. fix:

Sampler: 4x-UltraSharp

Hires steps: 6 ~ 10

Denoising strength: 0.5

Upscale by: 2 (resize from 512x768 to 1024x1536)

Clip skip: 2

CFG Scale: 7 ~ 8

VAE: kl-f8-anime2 VAE

Merge Recipe

Merged models are the following:

Delta Steps:

  1. Base = GoldenHarvest x 0.7 + FantasticChixHR x 0.7

  2. Delta = Base x 0.3 + DucHaitenNiji x 0.7

Swamp Steps:

  1. Base = GoldenHarvest x 0.7 + FantasticChixHR x 0.7

  2. Delta = Base x 0.5 + DucHaitenNiji x 0.5

Soul Steps:

  1. Base = GoldenHarvest x 0.7 + FantasticChixHR x 0.7

  2. Delta = Base x 0.7 + DucHaitenNiji x 0.3

License

All used models here have "Have different permissions when sharing merges" license permission, so I do not try to add any restriction on it.

CreativeML-Open Rail-M

This model permits users to:

✔Use the model without crediting the creator

✔Sell images they generate

✔Run on services that generate images for money

✔Share merges using this model

✔Sell this model or merges using this model

✔Have different permissions when sharing merges

Precedente
HIJKLMix - v4.0_pruned
Successivo
0001SoftRealistic - v82egVAEbaked
Usa questo modello

Dettagli del Modello

Tipo di modello

Checkpoint

Modello base

SD 1.5

Versione del modello

v3.0 Soul Baked VAE

Hash del modello

1429806246

Creatore

FadaSentava's avatar
FadaSentava

Discussione

Per favore log in per lasciare un commento.

Immagini di MixTape /// Blues - v3.0 Soul Baked VAE

AI generated image using Stable Diffusion of a woman with dark hair wearing a red jacket and pink scarf, holding a wrapped gift, standing in front of a snowy cityscape.

Immagini con modello base

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky Halloween cemetery filled with glowing jack-o'-lantern pumpkins and desiccated trees in a dark, foggy atmosphere.

Immagini con femmina

A white dragonborn female with red eyes and dragon horns, wearing an intricate robe and elaborate jewelry, standing in a stone balcony setting.
Portrait of a red dragonborn female with red scales, horns, and tail, wearing silver armor and pauldrons against a black background.
Milly, a female character with long brown hair and blue eyes, smiling with parted lips, wearing a collared shirt and brown pants with suspenders, seated on a couch indoors with desert landscape visible through the window.
Portrait of Milly, a female character with blue eyes and brown hair, wearing a green capelet, trench coat, and suspenders, standing in a desert landscape with sand dunes and ancient ruins.
A brown female dragonborn with dragon horns and braided hair standing in a sunlit wheat field, wearing a necklace, earrings, bracelets, and a detailed outfit, looking at the viewer with her hand raised.
Close-up stylized portrait of a female Will-o'-the-wisp with flowing caramel hair, captured in golden hour light, displaying an awe expression.
A female robot with white body and metal arms, glowing blue eyes, sitting on rubble in a ruined urban apocalypse cityscape under dark cloudy sky.
Futuristic cyborg girl with luminous neon white hair sitting cross-legged, viewed from below with mechanical limbs and glowing blue lighting in a dark cyberpunk city.
Rear view of an Egyptian female with white hair and red eyes kneeling in a desert under a large sun, wearing a white robe and Egyptian collar.
Portrait of a smiling woman with long red hair and blue eyes wearing a blue cloak with gold inlay outdoors.

Immagini con donna

Impressionist painting of a woman picking apples while standing barefoot on a wooden bench under an apple tree, wearing denim jeans and a plaid shirt.
A mysterious woman in a black dress walks confidently on a large chessboard surrounded by chess pieces under a dramatic stormy sky with dark clouds.
A female cyberpunk agent in a biomechanical skintight suit with glowing red tubes, standing in a rainy neon-lit urban alley at night.
Digital illustration of a confident blonde woman in a frill dress with hair partially up, standing against a pastel blue sky with fluffy clouds and blooming flowers.
Slim woman wearing a red long form-fitting dress with fringe and slit, black stockings, long black gloves, bob haircut, and dark futuristic glasses on her head, standing against a blue textured background.
A woman stands facing away towards a window in a dimly lit room, wearing a white off-shoulder dress and her hair tied up in a bun, bathed in soft natural light.
A woman wearing a polished aluminum space suit with a glass dome helmet and jetpack stands against a desert moon landscape with rocky formations and a large glowing moon behind her, showcasing perfect hair and AtomPunk style details.
Cyberpunk woman with short black hair and red eyes wearing a backless black dress showing prosthetic details, sitting by a window in a futuristic apartment.
A slender woman with brown messy hair in a ponytail, wearing a shiny teal raincoat, torn jeans, and leather boots, sitting on a large rock near a misty river bank with visible breath in cold air.
Close-up image of a woman's hazel eye showing detailed eyelashes, eye makeup, and natural facial skin texture.