Flux Sci-Fi Trained Image Generation

Discover Flux Sci-Fi Trained, an innovative AI model specializing in generating captivating science fiction images. Try it now and see the results!

Platform: Replicate

Sci-Fi DiffusionImage InpaintingLoRA Customization

169 runs

H100

License Check Required

🚀Function Overview

Generates and modifies science fiction-themed images using text prompts, image inputs, and masks with customizable parameters for fine-grained control over style and composition.

Key Features

Text-to-image generation with trigger word activation
Image-to-image and inpainting functionality via image and mask inputs
Multiple model options (dev/schnell) balancing quality vs speed
LoRA integration for applying custom styles/concepts
Adjustable dimensions, aspect ratios, and output quality settings
Guidance scale and prompt strength controls

Use Cases

•Creating sci-fi art and character concepts
•Photo editing via inpainting and style transfer
•Generating themed illustrations from text descriptions
•Prototyping game or film concept art

⚙️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": "A bright, ultra-realistic midshot of a pretty girl with orange white skin, long red braided hair, and wide gold eyes, wearing a tight silver bodysuit that hugs her curves. She’s leaning back against a cargo crate, one hand gripping the edge, the other pressed to her chest in stunned delight as her jaw drops. In front of her, a barbaric human hunter with a shaved head and thick stubble, wearing shredded tactical gear and a blood-smeared chest plate, is effortlessly lifting a massive fusion coil over his head with both hands. His veins bulge, and his mouth is twisted in a cocky grin as he stares directly at her. The setting is an open hangar bay on a jungle moon, humid steam curling around their feet, with glowing alien vines creeping through cracks in the floor and a red-orange sunset glowing through the cracked dome ceiling above. Her expression is a mix of disbelief and aroused fascination; his is raw confidence, practically challenging her to ask for more. The lighting is golden and dramatic, mid-body eye-level, capturing the heat of their tension mid-scene.\n\n\n\n\n\n\n\n",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "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/ijqY3u7m7mblEl72SJu4JpRf6I9kPezniaYIhATl3tXs6enpA/out-0.webp

Quick Actions

Use NowView Documentation

Technical Specifications

Hardware Type: H100
Run Count: 169
Commercial Use: Unknown/Restricted
Platform: Replicate

Related Keywords

text-to-image generationimage inpaintingLoRA customizationsci-fi artcharacter conceptsthemed illustrationsgame concept artfilm concept art

Related Models

Anju AI Art Generator

A model for generating and editing images through text prompts, inpainting, and aspect ratio customization.

CAMIS Image Generation

A model for generating and editing images using text prompts and input images with support for LoRA adapters.

Flash Beta 4

A model for generating and editing images with support for inpainting, image-to-image transformation, and custom LoRA style integration.