Modelo Raphael V3

Discover Modelo Raphael V3, a powerful image generation and editing model designed for ultimate creative freedom. Try it now and see the results!

Platform: Replicate

Image GenerationText-to-ImageImage InpaintingLoRA Customization

30 runs

H100

License Check Required

🚀Function Overview

A diffusion-based image generation and editing model that creates images from text prompts, modifies existing images through inpainting/masking, and incorporates LoRA weights for customized style effects.

Key Features

Text-to-image generation with trigger word activation
Image-to-image transformation with prompt strength control
Inpainting capabilities with mask inputs
Aspect ratio and resolution customization
Dual model options (quality-focused 'dev' vs speed-optimized 'schnell')
LoRA weight integration for style customization
Safety checker toggling
FP8 quantization for accelerated generation

Use Cases

•Creating artistic images from text descriptions
•Editing specific regions of images via inpainting
•Transferring styles using LoRA weights
•Generating profile portraits or concept art
•Rapid prototyping with fast generation mode

⚙️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": "modelo_raphael_v3 An artistic profile portrait of a man against a stark, dark background. Behind him, a large, glowing circle of vibrant warm light, like an intense orange sun, creates a dramatic halo effect. The man is in profile, facing towards the glowing circle. His face and body are dramatically lit from the front or side with a contrasting, cool-toned light, such as teal or deep blue, casting strong shadows and highlighting his features and form. The lighting emphasizes the contours of his face and the muscles of his upper body (if visible in the frame). The attire is minimal, perhaps bare-chested or wearing a simple top that allows the light to play on the skin and physique. The overall vibe is moody, stylized, and high-concept, focusing on the interplay of light, shadow, and color with a strong graphic element from the background circle. Shot with a focus on color contrast and dramatic lighting effects.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

Output Results

https://replicate.delivery/xezq/ui8vnPKi5gK8NJGcY8ff6jctHYqSr8U14a3wxwRt1t4RuNlUA/out-0.png

https://replicate.delivery/xezq/nNkLVZILGH7CNFer8nHgN6TURivxPYUiAuxGAqS1SRlI3mSKA/out-1.png

https://replicate.delivery/xezq/sdOMtoMsAHY3Ihioy5vYxhF0EpsSORru3PswYzsQMypkbTJF/out-2.png

https://replicate.delivery/xezq/GGdMTvhEjd4uG1yVOGfagY8jozZY46DHCifSVSMYEmiSuNlUA/out-3.png

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 30
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Image GenerationImage InpaintingLoRA CustomizationText-to-ImageImage EditingArtistic Image CreationStyle Transfer

Related Models

Helbert Costa Image Generation

A model for generating and modifying images using text prompts and LoRA weights.

Flash-Beta.6 Image Generation

A model for generating and editing images with advanced controls like inpainting, style adaptation, and LoRA-based customizations.

Pitiduval

A model for generating and editing images using text prompts and input images.