Flux Dev Lora

Rapid, high-quality image generation with FLUX.1 [dev] and LoRA support for personalized styles and brand-specific outputs

Features

flux-dev-lora is a 12 billion parameter rectified flow transformer capable of generating images from textual descriptions. For more information, please read our blog post.

Key Features

1. Competitive prompt following: Matches the performance of closed-source alternatives in understanding and executing prompts.
2. Efficient training with guidance distillation: This approach makes the model more efficient and responsive.
3. Open weights: Empowering new scientific research and enabling artists to develop innovative workflows.
4. Versatile usage: Outputs can be utilized for personal, scientific, and commercial purposes.

ComfyUI

flux-dev-lora is also available on ComfyUI, providing local inference capabilities through a node-based workflow, ensuring flexible and efficient image generation on your system.

Limitations

• The model is not designed to provide factual or verified information.
• Being a statistical model, it may amplify existing societal biases.
• Generated outputs might not always perfectly correspond to the given prompts.
• Prompt interpretation is strongly influenced by the phrasing of the input.

Out-of-Scope Use

The model and its derivatives may not be used in any way that violates applicable national, federal, state, local, or international law or regulation, including but not limited to:

• Exploiting, harming, or attempting to exploit or harm minors, including solicitation, creation, acquisition, or dissemination of child exploitative content.
• Generating or disseminating verifiably false information with the intent to harm others.
• Creating or distributing personal identifiable information that could be used to harm an individual.
• Harassing, abusing, threatening, stalking, or bullying individuals or groups.
• Producing non-consensual nudity or illegal pornographic content.
• Making fully automated decisions that adversely affect an individual’s legal rights or create binding obligations.
• Facilitating large-scale disinformation campaigns.

Accelerated Inference

Our accelerated inference approach leverages advanced optimization technology from WavespeedAI. This innovative fusion technique significantly reduces computational overhead and latency, enabling rapid image generation without compromising quality. The entire system is designed to efficiently handle large-scale inference tasks while ensuring that real-time applications achieve an optimal balance between speed and accuracy. For further details, please refer to the blog post.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v2/wavespeed-ai/flux-dev-lora" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "prompt": "Sexy blonde Christmas girl, wearing a revealing red Santa outfit with white fur trim, holding a gift box, festive lighting, soft glowing background, detailed skin texture, high contrast shadows, ultra-detailed face, cinematic atmosphere",
    "image": "",
    "strength": 0.8,
    "loras": [
        {
            "path": "linoyts/yarn_art_Flux_LoRA",
            "scale": 1
        }
    ],
    "size": "1024*1024",
    "num_inference_steps": 28,
    "guidance_scale": 3.5,
    "num_images": 1,
    "seed": -1,
    "enable_base64_output": true,
    "enable_safety_checker": true
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v2/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Query Parameters

Result Request Parameters

Result Response Parameters