WaveSpeed.ai
DashboardExploreInspiration
Home/Explore/Flux Image Tools/wavespeed-ai/flux-dev-lora

text-to-image

wavespeed-ai/flux-dev-lora

Super fast endpoint for the FLUX.1 [dev] model with LoRA support, enabling rapid and high-quality image generation using pre-trained LoRA adaptations for personalization, specific styles, brand identities, and product-specific outputs.

Hint: You can drag and drop a file or click to upload

Hint: You can drag and drop a file or click to upload

Recommend:
strangerzonehf/Flux-Super-Realism-LoRA
linoyts/yarn_art_Flux_LoRA
lichorosario/flux-lora-total-drama-character
width
height
If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Idle

Super Realism, Woman in a red jacket, snowy, in the style of hyper-realistic portraiture, caninecore, mountainous vistas, timeless beauty, palewave, iconic, distinctive noses --ar 72:101 --stylize 750 --v 6

Your request will cost $0.015 per run.

For $1 you can run this model approximately 66 times.

One more thing:

ExamplesView all

Super Realism, Woman in a red jacket, snowy, in the style of hyper-realistic portraiture, caninecore, mountainous vistas, timeless beauty, palewave, iconic, distinctive noses --ar 72:101 --stylize 750 --v 6
A glowing, ethereal figure floats in the dark space, making it look almost like an angel. It has a calm and peaceful feeling, as if exuding a peaceful atmosphere, and its wings are composed of white light. This figure is completely composed of a soft and delicate beam of energy, which has an impressionist effect on the surrounding environment.
Octopus vs. lam chess game, underwater setting, vibrant colors
The sun shines all over the courtyard, and the breeze blows gently, bringing bursts of flowers. Several girls were dressed in fine gauze and their skirts were blown by the wind, chasing and playing in the garden. Their laughter is as clear as a silver bell, sometimes jumping and sometimes spinning, like a group of dancing butterflies. One girl held a wreath and put it gently on her companion's head, while the other hid behind a tree and sneaked out her head, her eyes shining with naughty light. Their figures are looming in the flowers, sometimes holding hands and sometimes separating, as if they were integrated with the surrounding nature. The air is filled with youthful vitality and carefree happiness, as if this moment of time will never pass.The girl is a small dance in Douro Mainland.
a cat
a cat
yarn art style, Sexy blonde Christmas girl, wearing a revealing red Santa outfit with white fur trim, holding a gift box, festive lighting, soft glowing background,
an elderly man sitting by a window, warm sunlight casting soft shadows, ultra-realistic, high detail skin texture, weathered hands, cinematic photography, depth of field, 50mm lens, cozy room interior, storytelling mood
a traveler standing on a hilltop at sunrise, light wind blowing through her hair, ultra-realistic lighting, soft golden glow, bright clear sky, detailed fabric, serene atmosphere, realistic landscape, cinematic photo realism
a stylish woman sitting by a window, reading a book, sunlight streaming in, ultra-realistic, bright soft lighting, cozy modern interior, subtle skin texture, natural smile, casual elegance, lifestyle photography, crisp details, 85mm lens
a young woman with long flowing hair walking through a sunlit park, cherry blossoms falling, ultra-realistic, soft sunlight, clear blue sky, radiant smile, cinematic lighting, glowing skin, dreamy atmosphere, vibrant colors, 85mm lens

README

Flux-dev-lora

FLUX.1 [dev] is a 12B parameter rectified flow transformer for advanced text-to-image generation. It supports prompt-only generation as well as image inpainting and LoRA customization, making it a flexible tool for both research and creative workflows.

Why it looks great

  • High-quality output: Cutting-edge visual fidelity, second only to FLUX.1 [pro].
  • Prompt alignment: Strong competitive prompt following, rivaling closed-source alternatives.
  • Efficient training: Trained with guidance distillation for better speed-performance balance.
  • Flexible editing: Supports image + mask editing, LoRA fine-tuning, and custom strength control.
  • Open weights: Enables research, experimentation, and innovative creative pipelines.

Limits and Performance

  • Max resolution: up to 1536 × 1536 pixels

  • Optional inputs:

    • image (for img2img)
    • mask_image (for inpainting)

  • LoRA support: add multiple .safetensors with adjustable scale

  • Inference controls:

    • num_inference_steps (default ~28)
    • guidance_scale (default ~3.5)
    • strength (the strength of transform the reference image)

  • Output format: JPEG / PNG / WEBP

  • Seed: reproducibility (-1 = random)

Pricing

Just $0.015 per image !!

How to Use

  1. Write a prompt — detailed scene + style (lighting, realism, mood).

  2. (Optional) Upload an image to guide generation.

  3. (Optional) Add a mask image for inpainting.

  4. Adjust parameters:

    • Strength (the strength of transform the reference image).
    • LoRAs (add path/URL + scale).
    • Size (width & height, up to 1024×1024).
    • Inference steps and guidance scale.

  5. Set num_images (default 1).

  6. (Optional) Fix seed for reproducibility.

  7. Choose output format and run.

Pro tips

  • Use higher inference steps for more detail, lower for speed.
  • Adjust guidance scale to balance prompt strength vs. creativity (3–7 recommended).
  • Apply mask + strength for clean local edits (inpainting).
  • Blend multiple LoRAs for hybrid style outputs.
  • Use consistent seeds when testing parameter changes for controlled comparison.

Notes

  • The image URL must be valid and accessible; otherwise, the job may fail.
  • For mask_image, do not upload the original or unprocessed image directly — ensure the mask is correctly prepared.
  • LoRA files must be uploaded from trusted platforms and set to public access to be usable.
  • Parameters such as num_inference_steps (and others) directly affect runtime: the larger the value, the longer the generation will take.

Reference