Text to Image
Create high quality images from text using the FLUX model.
POST
Text-to-Image

You can apply LoRA models to your FLUX generations using the
lora_model parameter. To use multiple LoRAs, pass comma-separated LoRA model IDs to lora_model (e.g. "more_details,animie") and matching comma-separated weights to lora_strength (e.g. "0.8,0.6").Request
Make aPOST request to the endpoint below with the required parameters.
Parameters
Your API key for authentication. Get one from your dashboard.
Text description of the image you want to generate. Be specific and detailed for best results.
Number of denoising steps. Higher values produce more detailed images but take longer. Range: 20-50.
How closely to follow the prompt. Higher values = more literal interpretation. Range: 1-20.
Random seed for reproducible results. Use the same seed with same parameters to get identical images.
The LoRA model ID to apply during generation. For multiple LoRAs, pass comma-separated model IDs, e.g.
"more_details,animie".The strength (weight) applied to the LoRA model. For multiple LoRAs, pass comma-separated values matching the order of
lora_model, e.g. "0.8,0.6".URL to receive a POST request when generation completes. See Webhooks.
Request Example
Response
Success Response
When the image is generated successfully:Processing Response
For complex requests, you may receive a processing status:Error Response
Response Fields
Tips for Better Results
Write Detailed Prompts
Write Detailed Prompts
FLUX responds well to detailed, specific prompts. Include:
- Subject description
- Style (photorealistic, cinematic, etc.)
- Lighting details
- Camera settings (for photorealistic images)
Use Negative Prompts
Use Negative Prompts
Always include a negative prompt to avoid common issues:
Adjust Guidance Scale
Adjust Guidance Scale
- Lower (3-7): More creative, varied results
- Higher (8-15): More literal prompt adherence
- Default (7.5): Good balance for most use cases
Apply LoRA Models
Apply LoRA Models
Use the
lora_model parameter to apply a LoRA and fine-tune the style or subject of your generation:- Pass a single LoRA ID, e.g.
"more_details". - For multiple LoRAs, pass comma-separated IDs to
lora_modeland matching weights tolora_strength. - Tune
lora_strength(typically0.6–1.0) to control how strongly each LoRA is applied.
Related Endpoints
Image to Image
Transform existing images with FLUX
Fetch Results
Retrieve results for processing requests
Body
application/json
Available schedulers for image generation.
Available options:
DDPMScheduler, DDIMScheduler, PNDMScheduler, LMSDiscreteScheduler, EulerDiscreteScheduler, EulerAncestralDiscreteScheduler, DPMSolverMultistepScheduler, HeunDiscreteScheduler, KDPM2DiscreteScheduler, DPMSolverSinglestepScheduler, KDPM2AncestralDiscreteScheduler, UniPCMultistepScheduler, DDIMInverseScheduler, DEISMultistepScheduler, IPNDMScheduler, KarrasVeScheduler, ScoreSdeVeScheduler, LCMScheduler Response
Text-to-image generation response
- Option 1
- Option 2
- Option 3

