G
GetLLMs

Carlos Image Generator

Discover the power of Carlos Image Generator, a versatile model for creating stunning visuals from text, inpainting, and applying LoRA styles.

Platform: Replicate
Image SynthesisInpaintingLoRA StylizationThumbnail Generation
11 runs
H100
License Check Required

🚀Function Overview

Generates or modifies images using text prompts with options for aspect ratio control, quality adjustment, and LoRA-based style customization across fast or precision modes.

Key Features

  • Text-to-image generation with prompt-trigger customization
  • Image inpainting via mask and image inputs
  • LoRA support for style transfer and fine-tuning
  • Fast generation mode with optimized performance
  • Detailed control over resolution, aspect ratio and output quality

Use Cases

  • Creating social media thumbnails
  • Stylized content generation using LoRA models
  • Product image enhancements
  • AI-assisted graphic design workflows

⚙️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

{
  "image": "https://img.youtube.com/vi/P_Gv_YZ362Y/maxresdefault.jpg",
  "model": "dev",
  "prompt": "Design a high-impact YouTube thumbnail featuring Carlos, a confident fit man with slicked-back salt-and-pepper hair, a strong jawline, and a composed expression. He is sitting at a desk, wearing a black button-up shirt, and confidently pointing at a laptop screen in front of him.\n\nOn the laptop screen, display a glowing Amazon FBA logo (instead of Binance). Behind Carlos, use a dark background with a glowing yellow upward graph line, implying growth and success. Add digital-style elements like plus signs or data lines to give it a tech/financial vibe.\n\nAt the top left of the thumbnail, add bold, high-contrast text:\n\nAMAZON FBA (gradient yellow to white)\n$100,000 (bold white)\n\nMake the overall aesthetic clean, modern, and eye-catching—ideal for a video about Amazon success or financial wins with FBA.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "16:9",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/oRNPsubMn061DBj76ATVulGoddqX1K80mS5HopEc7FwByYNF/out-0.webp
https://replicate.delivery/xezq/xAT3QD3fMTUBNyfe1BaMffHnzoHIJhIkSeUBWl06iwtxByYNF/out-1.webp
https://replicate.delivery/xezq/d6u5ne6ufqq1jkAneUbKfKgh44Oo6OKfoLJfaz7d4Zy9ByYNF/out-2.webp
https://replicate.delivery/xezq/N56X7hBGn9oJKF7wozIlGXf5eVANpS6o1I2zH9eqDBUOQGrpA/out-3.webp