ghost
Sign In

MixTape /// Funk

1.1k
8.9k
97
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
1,141
Reviews
Published
Jul 15, 2023
Base Model
SD 1.5
Hash
AutoV2
ECF02D3110

Beauty and sensuality in every illustration. Let yourself be carried away by a world of fantasy and desire, where each stroke reveals a seductive story. Your wildest fantasies come to life in vibrant colors and immersive details.

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

Just like funk music, images are a vibrant and expressive form of art that offer a diversity of visual experiences.

Images can be energetic and impactful, conveying a sense of movement and rhythm through lines and colors. They have the power to evoke intense emotions, much like the infectious rhythm of funk music can make people dance and have fun.

The aim of this model is to create illustrations that, just like a funky beat resonating in the body, can capture the viewer's attention and ignite their imagination.

The Melody version has a strong contrast between light and shadow and can achieve more exaggerated proportions of human anatomy.

The Ostentação version has more realistic proportions, and a less smudged finish. It has made a greater variation of faces and has shown good quality in the generation of hands.

The Proibidão version has the most realistic proportions in this series. The lighting is softer and it's still capable of creating images with a lot of detail in the composition.

Recommends

Positive Prompt:

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

Negative Prompt:

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), (loli:1.2), ...

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

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: vae-ft-mse-840000-ema-pruned.ckpt

Merge Recipe

Merged models are the following:

Melody Steps:

  1. BaseModelA = XXMix_9realistic x 0.7 + DucHaitenNiji x 0.3

  2. BaseModelB = Shadow97's Beta+ x 0.7 + Puffy x 0.3

  3. MixTape = BaseModelA x 0.3 + BaseModelB x 0.7

Ostentação Steps:

  1. BaseModelA = XXMix_9realistic x 0.7 + DucHaitenNiji x 0.3

  2. BaseModelB = Shadow97's Beta+ x 0.7 + Puffy x 0.3

  3. MixTape = BaseModelA x 0.5 + BaseModelB x 0.5

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