Flux Dev Lora
Rapid, high-quality image generation with FLUX.1 [dev] and LoRA support for personalized styles and brand-specific outputs.
What it does
Flux Dev Lora, in practice.
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.
- 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.
- 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.
Run Flux Dev Lora
from $0.022/imageParameters
What you can set.
| Parameter | What it does | Options |
|---|---|---|
seed | Random seed (-1 for random) | default -1 |
size | Output image size | default 1024*1024 |
image | ||
loras | List of LoRAs to apply (max 5) | |
prompt | Input prompt for image generation | |
strength | Strength indicates extent to transform the reference image | default 0.8 |
mask_image | The mask image tells the model where to generate new pixels (white) and where to preserve the original image (black). It acts as a stencil or guide for targeted image editing. | |
num_images | Number of images to generate | default 1 |
guidance_scale | Flux embedded guidance strength. Higher values make the image follow the prompt more closely. This is not True CFG and does not require a negative prompt. Default 2.5. | default 2.5 |
cfg_scale | True classifier-free guidance. Keep at 1.0 (off) for normal use. Set it above 1.0 to enable negative prompting; a non-empty negative_prompt requires cfg_scale > 1, otherwise the request is rejected. On its own (with an empty negative_prompt | default 1.0 |
negative_prompt | What to steer the image away from. Only takes effect when cfg_scale > 1; setting a non-empty negative_prompt while cfg_scale <= 1 is rejected with HTTP 400. | |
num_inference_steps | The number of inference steps to perform. | default 28 |
Sample prompt
The prompt behind the sample.
A quiet residential street covered in fresh snow at dusk, Japanese suburban neighborhood with small houses, warm light glowing from windows, snow piled along the road, wet asphalt reflecting soft sky colors. A black cat sitting in the foreground, looking down the street. Overhead power lines and street lamps framing the scene, birds flying across a pale blue winter sky. Calm, peaceful atmosphere, cinematic composition, soft natural lighting, ultra-detailed environment, painterly realism, high-quality illustration, depth and perspective
seed: -1size: 1024*1024strength: 0.8num_images: 1guidance_scale: 3.5num_inference_steps: 28enable_base64_output: enable_safety_checker: TrueFAQ
Short answers.
How much does Flux Dev Lora cost?
Pricing starts at $0.022 per image at the base resolution; higher resolutions and longer durations cost more. Usage is billed per request from your balance — no subscription.
Does Flux Dev Lora run uncensored here?
No. Black Forest Labs applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists Flux Dev Lora for everything else it does well.
What does Flux Dev Lora take as input?
It is a text-to-image model. Rapid, high-quality image generation with FLUX.1 [dev] and LoRA support for personalized styles and brand-specific outputs.
How do I use it?
Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.
Related