---
title: "flux-dev-lora"
url: "https://docs.api.pruna.ai/apis/models-api-0/versions/7dfbc266-0f94-4c90-8518-d9e4d1a245ec/schemas/flux-dev-lora"
---

> Full API specification: https://docs.api.pruna.ai/apis/models-api-0/versions/7dfbc266-0f94-4c90-8518-d9e4d1a245ec.md

# flux-dev-lora

AI model for content generation. Rate limit: 150 requests per minute.

## OpenAPI definition

```yaml
openapi: 3.0.3
info:
  title: P-API
  version: 0.3.0
servers:
  - url: https://api.pruna.ai
    description: Production server
components:
  schemas:
    flux-dev-lora:
      type: object
      required:
        - input
      properties:
        input:
          type: object
          properties:
            lora:
              title: Lora
              description: Load LoRA weights. Supports HuggingFace URLs in the format
                <owner>/<model-name>[/<lora-weights-file.safetensors>]. For
                example, 'fofr/flux-pixar-cars'.
              type: string
            seed:
              title: Seed
              description: Random seed. Set for reproducible generation
              type: integer
            image:
              title: Image
              format: uri
              description: Input image for image to image mode. The aspect ratio of your
                output will match this image
              type: string
            prompt:
              title: Prompt
              description: Prompt for generated image
              type: string
            guidance:
              title: Guidance
              default: 3
              maximum: 10
              minimum: 0
              description: Guidance for generated image
              type: number
            extra_lora:
              title: Extra Lora
              description: Load LoRA weights. Supports HuggingFace URLs in the format
                <owner>/<model-name>[/<lora-weights-file.safetensors>]. For
                example, 'fofr/flux-pixar-cars'.
              type: string
            lora_scale:
              title: Lora Scale
              default: 1
              maximum: 3
              minimum: -1
              description: 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.
              type: number
            megapixels:
              enum:
                - "1"
                - "0.25"
              title: megapixels
              description: Approximate number of megapixels for generated image
              default: "1"
              type: string
            speed_mode:
              enum:
                - Base Model (compiled)
                - Lightly Juiced 🍊
                - Juiced 🧃
                - Extra Juiced 🔥
              title: speed_mode
              description: Speed optimization level
              default: Juiced 🧃
              type: string
            num_outputs:
              title: Num Outputs
              default: 1
              maximum: 4
              minimum: 1
              description: Number of outputs to generate
              type: integer
            aspect_ratio:
              enum:
                - 1:1
                - 16:9
                - 21:9
                - 3:2
                - 2:3
                - 4:5
                - 5:4
                - 3:4
                - 4:3
                - 9:16
                - 9:21
              title: aspect_ratio
              description: Aspect ratio of the output image
              default: 1:1
              type: string
            output_format:
              enum:
                - png
                - jpg
                - webp
              title: output_format
              description: Format of the output images
              default: jpg
              type: string
            output_quality:
              title: Output Quality
              default: 80
              maximum: 100
              minimum: 1
              description: Quality when saving the output images, from 0 to 100. 100 is best
                quality, 0 is lowest quality. Not relevant for .png outputs
              type: integer
            prompt_strength:
              title: Prompt Strength
              default: 0.8
              maximum: 1
              minimum: 0
              description: Prompt strength when using img2img. 1.0 corresponds to full
                destruction of information in image
              type: number
            extra_lora_scale:
              title: Extra Lora Scale
              default: 1
              maximum: 3
              minimum: -1
              description: 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.
              type: number
            num_inference_steps:
              title: Num Inference Steps
              default: 28
              description: Number of denoising steps. Recommended range is 28-50, and lower
                number of steps produce lower quality outputs, faster.
              type: integer
          required:
            - prompt
          additionalProperties: false
      description: "AI model for content generation. Rate limit: 150 requests per minute."
```