Fluxgram XD1 Image Generator

Unleash your creativity with Fluxgram XD1 Image Generator. Generate and edit images using text prompts, with advanced inpainting and LoRA integration.

Platform: Replicate

Stable DiffusionImage InpaintingLoRA IntegrationImage-to-Image

61 runs

H100

License Check Required

🚀Function Overview

Generates and edits images based on text prompts, supports inpainting, aspect ratio customization, model selection for speed/quality tradeoffs, and LoRA-based style adjustments.

Key Features

Text-to-image generation with prompt customization
Image-to-image transformation via img2img
Inpainting using mask inputs
Custom aspect ratios and resolutions
Choice between 'dev' (quality) or 'schnell' (speed) models
LoRA integration for style/object customization
Adjustable denoising steps and guidance scale
Output format/quality controls

Use Cases

•Creating photorealistic scenes from text descriptions
•Editing existing images through inpainting
•Applying custom artistic styles via LoRA weights
•Generating image variations for creative projects

⚙️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": "26-year-old woman with long, wavy blonde hair, emerald green eyes, fit body, dewy skin, wearing a flowing crimson Versace gown with gold embroidery, standing confidently on a Santorini cliffside overlooking the Aegean Sea at sunset, golden hour light casting soft shadows, photorealistic, 8K resolution, hyper-detailed, shot with Canon EOS R5, shallow depth of field, cinematic lighting",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "4:3",
  "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/MTGOVHFY1P7WO9Wjr2IkEUOAPpKlfyVyjQQV92XlNB1HaxaKA/out-0.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 61
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

Text-to-Image GenerationImage-to-Image TransformationInpaintingLoRA IntegrationCustom Aspect RatiosModel SelectionPrompt Customization

Related Models

Sokolovski Image Generation

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

Luma Portrait

A model for generating portrait images with specific styles and enhancements.

Italian Brainrot AI Image Generator

A model for generating and manipulating images through text prompts, image inputs, and inpainting capabilities.