G
GetLLMs

Lays V2.5 Rococo Sci-Fi Gothic Image Generator

Unleash your creativity with Lays V2.5 Rococo Sci-Fi Gothic Image Generator. Ready to experience the power of AI? Start your journey here!

Platform: Replicate
Rococo ArtSci-Fi GothicImage InpaintingLoRA Support
274 runs
H100
License Check Required

🚀Function Overview

An AI image generation model specializing in Rococo painting styles with sci-fi and gothic elements, supporting image-to-image transformations, inpainting, and custom artistic controls.

Key Features

  • Generates images in Rococo painting style with sci-fi gothic aesthetics
  • Supports image inpainting and image-to-image transformations
  • Adjustable aspect ratios, resolutions, and output formats
  • LoRA integration for custom style adaptations
  • Fine-grained control over generation speed (fp8 vs bf16 modes)
  • Configurable denoising steps and guidance scale
  • Optional safety checker disablement

Use Cases

  • Creating sci-fi gothic art in Rococo painting style
  • Modifying existing images through inpainting masks
  • Generating high-resolution concept art with specific thematic elements
  • Producing LoRA-enhanced artistic variations

⚙️Input Parameters

prompt

string

Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.

image

string

Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.

mask

string

Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.

aspect_ratio

string

Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode

height

integer

Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation

width

integer

Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation

prompt_strength

number

Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image

model

string

Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.

num_outputs

integer

Number of outputs to generate

num_inference_steps

integer

Number of denoising steps. More steps can give more detailed images, but take longer.

guidance_scale

number

Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5

seed

integer

Random seed. Set for reproducible generation

output_format

string

Format of the output images

output_quality

integer

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

disable_safety_checker

boolean

Disable safety checker for generated images.

go_fast

boolean

Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16

megapixels

string

Approximate number of megapixels for generated image

lora_scale

number

Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

extra_lora

string

Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'

extra_lora_scale

number

Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "dev",
  "prompt": "in the international style of TOK, \n\nIn the international style of TOK, a deep blue background. A large oval takes up most of the scene. Cropped within. Inside, a rococo dinner scene closeup. Front and center is a highly detailed artistic, oval shaped representation of Earth as a celestial artifact. The main body is a luminous cobalt blue sphere with intricate textural ripples resembling oceanic currents carved across its entire surface., radiating outward like a pumpkin. Scattered across this azure expanse are irregular patches of gleaming gold leaf representing abstract continental forms - larger masses suggesting Eurasia and Africa in the northern hemisphere, the Americas along one side, and smaller golden fragments depicting Australia and Pacific archipelagos. The delicate swirling patterns etched into the surface suggest global wind patterns and major ocean currents circumnavigating the planet. The sphere rests upon a clear crystal base. \n\nThe monochromatic dark blue-tinted lighting on technological elements contrasting with warm chiaroscuro on organic gemstones, translucent enamel containing starry cosmic particles, metallic gold filigree and adornments resembling microchips against deep black background. Atmospheric cinematic lighting with warm deep amber undertones, film grain overlay, shallow depth of field, inspired by biomechanical religious horror and transhumanist ceremonial procedures, reminiscent of Cronenberg and H.R. Giger aesthetics, photorealistic, 8K resolution, shot on Arri Alexa with vintage anamorphic lenses photorealistic rendering with sci-fi mechanical details, melancholic yet reverent mood, ancient wooden altar surface displaying both natural grain and embedded circuitry --ar 4:5 --v 6 --s 1000 --q 2 --style raw Ed",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "4:5",
  "output_format": "webp",
  "guidance_scale": 0,
  "output_quality": 100,
  "prompt_strength": 0.72,
  "extra_lora_scale": 1,
  "num_inference_steps": 47
}

Output Results

https://replicate.delivery/xezq/MpGu5ZsejAzWIa7tfwVfgEPSfSJbYCbJo7Kd8B0Zzfo6mTOlC/out-0.webp
https://replicate.delivery/xezq/xeEJWevzhivMs0pSIstLYwGjCJRf8RZSkfIf5ZNzY76eNncKF/out-1.webp
https://replicate.delivery/xezq/Fsf3XQJ4LMTcXqDAG2UekpUSYyAGqHi1nK1ZVvkDzMy3cypUA/out-2.webp
https://replicate.delivery/xezq/xy51sfGnoD3re0ss4VUpeTUNf7sQkS1XsZM8CM05XJ5fmTOlC/out-3.webp