Flux Dev LoRA - Image Generator

Professional LoRA-enabled AI image generation model by Black Forest Labs. Flux Dev LoRA combines balanced quality and speed with advanced LoRA support, dual LoRA loading, image-to-image generation, and external API access for comprehensive creative workflows.

Endpoint

POSThttps://api.1min.ai/api/features

Request Headers

Field	Value
API-KEY	<api-key>
Content-Type	application/json

Parameters

Parameter	Type	Required	Description
type	string	Yes	Feature type identifier. Must be IMAGE_GENERATOR
model	string	Yes	AI model identifier. Must be black-forest-labs/flux-dev-lora
promptObject	object	Yes	Configuration object containing all generation parameters

Prompt Object Parameters

Parameter	Type	Required	Description	Default
prompt	string	Yes	Text description of the image to generate	-
image_prompt	string	No	Path to input image from Asset API for image-to-image generation	-
aspect_ratio	string	No	Image aspect ratio (1:1, 16:9, 9:16, 3:2, 2:3, 4:5, 5:4, custom)	1:1
prompt_strength	number	No	Influence of prompt vs input image (0-1)	0.8
num_inference_steps	number	No	Number of inference steps (1-50)	28
guidance	number	No	Guidance scale for prompt adherence (0-50)	3.5
seed	number	No	Random seed for reproducibility (0-4294967295)	Random
output_quality	number	No	Output image quality (0-100)	80
disable_safety_checker	boolean	No	Disable built-in safety filtering	false
go_fast	boolean	No	Enable fastest generation mode	false
lora_weights	string	No	Primary LoRA model identifier	-
lora_scale	number	No	Primary LoRA influence strength (0-3)	1
extra_lora	string	No	Secondary LoRA model identifier	-
extra_lora_scale	number	No	Secondary LoRA influence strength (0-3)	1
megapixels	string	No	Output resolution in megapixels (0.25, 1, 2)	1
hf_api_token	string	No	HuggingFace API token for private models	-
civitai_api_token	string	No	CivitAI API token for private models	-

Supported Aspect Ratios

Ratio	Use Case
1:1	Square images, social media posts
16:9	Widescreen, video thumbnails
9:16	Vertical video, mobile screens
3:2	Standard photography
2:3	Portrait photography
4:5	Instagram posts
5:4	Landscape photography
custom	Use specific width/height values

Advanced LoRA Features

Feature	Description
Dual LoRA Loading	Load two LoRA models simultaneously for complex styles
Image-to-Image + LoRA	Apply LoRA styles to existing images
External API Access	Access private LoRA models with HF/CivitAI tokens
Independent Scaling	Control each LoRA's influence separately

LoRA Sources

Source	Token Required	Example
HuggingFace	hf_api_token	user/model-name
CivitAI	civitai_api_token	civitai.com/models/12345
Public Models	None	fofr/flux-80s-cyberpunk

Quality Settings

Setting	Range	Description
Inference Steps	1-50	More steps = higher quality but longer generation time
Guidance	0-50	How closely to follow the prompt (higher = more adherence)
LoRA Scale	0-3	Primary LoRA influence strength
Extra LoRA Scale	0-3	Secondary LoRA influence strength
Megapixels	0.25, 1, 2	Output resolution (2MP max for detailed work)

Code Examples

cURL

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "IMAGE_GENERATOR",
"model": "black-forest-labs/flux-dev-lora",
"promptObject": {
  "prompt": "Cyberpunk street scene with neon lights, futuristic architecture",
  "aspect_ratio": "1:1",
  "num_inference_steps": 28,
  "guidance": 3.5,
  "lora_weights": "fofr/flux-80s-cyberpunk",
  "lora_scale": 1,
  "megapixels": "1"
}
}'

JavaScript

fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
  'Content-Type': 'application/json',
  'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
  type: 'IMAGE_GENERATOR',
  model: 'black-forest-labs/flux-dev-lora',
  promptObject: {
    prompt: 'Cyberpunk street scene with neon lights, futuristic architecture',
    aspect_ratio: '1:1',
    num_inference_steps: 28,
    guidance: 3.5,
    lora_weights: 'fofr/flux-80s-cyberpunk',
    lora_scale: 1,
    megapixels: '1'
  }
})
})

Python

import requests

url = "https://api.1min.ai/api/features"
headers = {
"Content-Type": "application/json",
"API-KEY": "YOUR_API_KEY"
}

data = {
"type": "IMAGE_GENERATOR",
"model": "black-forest-labs/flux-dev-lora",
"promptObject": {
  "prompt": "Cyberpunk street scene with neon lights, futuristic architecture",
  "aspect_ratio": "1:1",
  "num_inference_steps": 28,
  "guidance": 3.5,
  "lora_weights": "fofr/flux-80s-cyberpunk",
  "lora_scale": 1,
  "megapixels": "1"
}
}

response = requests.post(url, headers=headers, json=data)

Interactive Playground

API Playground

GETPOSTPUTDELETEhttps://api.1min.ai/api/features

AI Model *Flux Dev LoRA - Black Forest Labs

Prompt *

Describe the image you want to generate

Cyberpunk street scene with neon lights, futuristic architecture

Image Prompt

Path to input image from Asset API for image-to-image generation

Aspect Ratio

Choose aspect ratio for your image

1:1 - Square16:9 - Widescreen9:16 - Vertical video3:2 - Photography2:3 - Portrait4:5 - Instagram5:4 - Landscape

Prompt Strength

Influence of prompt vs input image (0-1)

Num Inference Steps

Number of inference steps (1-50)

Guidance

Guidance scale for prompt adherence (0-50)

LoRA Weights

Primary LoRA model identifier

LoRA Scale

Primary LoRA influence strength (0-3)

Extra LoRA

Secondary LoRA model identifier

Extra LoRA Scale

Secondary LoRA influence strength (0-3)

Megapixels

Output resolution in megapixels

0.25 MP (~512×512)1 MP (~1024×1024)2 MP (~1448×1024)

Go Fast

Enable fastest generation mode

TrueFalse

Disable Safety Checker

Disable built-in safety filtering

TrueFalse

HF API Token

HuggingFace API token for private models

CivitAI API Token

CivitAI API token for private models

Output Quality

Output image quality (0-100)

Seed

Random seed for reproducibility (0-4294967295)

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
  -H "API-KEY: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "IMAGE_GENERATOR",
  "model": "black-forest-labs/flux-dev-lora",
  "promptObject": {
    "prompt": "Cyberpunk street scene with neon lights, futuristic architecture",
    "aspect_ratio": "1:1",
    "prompt_strength": 0.8,
    "num_inference_steps": 28,
    "guidance": 3.5,
    "lora_weights": "fofr/flux-80s-cyberpunk",
    "lora_scale": 1,
    "megapixels": "1"
  }
}'

Response Format

{
"aiRecord": {
  "uuid": "e4f5g6h7-i8j9-0123-4567-890123defghi",
  "userId": "user-12345",
  "teamId": "team-67890",
  "model": "black-forest-labs/flux-dev-lora",
  "type": "IMAGE_GENERATOR",
  "status": "SUCCESS",
  "createdAt": "2025-01-15T10:50:00.000Z",
  "aiRecordDetail": {
    "promptObject": {
      "prompt": "Cyberpunk street scene with neon lights, futuristic architecture",
      "aspect_ratio": "1:1",
      "num_inference_steps": 28,
      "guidance": 3.5,
      "lora_weights": "fofr/flux-80s-cyberpunk",
      "lora_scale": 1,
      "megapixels": "1"
    },
    "resultObject": [
      "development/images/2025_01_15_10_50_45_001_cyberpunk_scene.webp"
    ]
  },
  "temporaryUrl": "https://s3.us-east-1.amazonaws.com/asset.1min.ai/development/images/2025_01_15_10_50_45_001_cyberpunk_scene.webp?X-Amz-Algorithm=AWS4-HMAC-SHA256&..."
}
}

Use Cases

• Professional Design: High-quality styled imagery for commercial projects
• Style Transfer: Apply artistic styles to existing images with LoRA + img2img
• Brand Development: Consistent visual identity using custom LoRAs
• Creative Workflows: Balanced quality and speed for iterative design
• Multi-Style Blending: Combine multiple LoRA effects for unique aesthetics

Tips for Best Results

1. Dual LoRA Strategy:

   • Primary LoRA: Main style or aesthetic (scale 0.8-1.2)
   • Secondary LoRA: Enhancement or detail refinement (scale 0.5-1.0)
   • Balance scales to avoid over-styling

2. Image-to-Image with LoRA:

   • Use prompt strength 0.6-0.8 for balanced transformation
   • Apply complementary LoRAs to enhance source image style
   • Higher guidance (4-6) for more controlled results

3. External Model Access:

   • Use HF API tokens for private HuggingFace models
   • CivitAI tokens enable access to community-created LoRAs
   • Test public models first before using private ones

Notes

Advanced LoRA Features

This model supports dual LoRA loading and external API access. Combine multiple styles or access private models for enhanced creative control.