Sign In

MixTape /// Salsa

375
2.8k
14.5k
48
Verified:
SafeTensor
Type
Checkpoint Merge
Stats
483
8
Reviews
Published
Mar 17, 2024
Base Model
SD 1.5
Usage Tips
Clip Skip: 2
Hash
AutoV2
02E952D650

Allow yourself to be enveloped by sensuality and let passion guide your way. Feel the rhythm, embrace the freedom, and create with all your heart. 💃🔥🎨

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

Immerse yourself in a world where the sensuality of dance intertwines with the freedom of artistic expression. Celebrating life, music, and passion. Let yourself be carried away by the pulsating beat of salsa, where sensuality flows like a fiery river, and dance becomes a manifestation of pure emotion.

This model is your soundtrack for creation. Draw inspiration from the vibrant energy of colors, the gentle curves of shapes, and the passion that transcends each image. Here, art blends with rhythm, allowing your creativity to break free, just like a dancer surrendering to the music.

The Fusão version generates anime-style 2D images with vibrant colors and fine lines. Short prompts have generated great results.

The Dura version has a more realistic touch and smoother lines. It still has vibrant colors and lots of details.

The Urbana version has the most realistic proportions in this collection. With smooth lines and natural lighting, this version delivers outstanding results, particularly in materials like clothing, where intricate details matter.

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:

  • gy010

  • Aniverse

Fusão:

  1. Fusão = gy010 x 0.7 + Aniverse x 0.3

Dura:

  1. Dura = gy010 x 0.5 + Aniverse x 0.5

Urbana:

  1. Urbana = gy010 x 0.3 + Aniverse x 0.7

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