FLUX API

FLUX family on Replicate — Schnell, Dev, Pro, Kontext, Ultra, and LoRA remix variants in one entrypoint. Integrate this model via REST with endpoint docs, parameters, and code examples.

Image Generation

Img2Img

LoRA

Content moderation disabled

Credit Cost

1 credit

Type

image

Get API Key

Create auth keys for apps and agents

See Usage

Track requests, credits, and logs

Buy Credits

Top up prepaid API capacity

Try a preset

Pre-tuned starting points. Click one to open the tool with these params loaded.

Architectural twilight

Modern architecture exterior, blue hour, long-exposure light trails.

Try this preset

Cinematic portrait

Moody close-up portrait, shallow depth of field, golden hour rim light.

Try this preset

Concert stage

Wide concert venue from the back, performer silhouette, audience phones up.

Try this preset

Desert fashion

Editorial fashion shot in a desert setting at golden hour, wind in the hair.

Try this preset

Editorial coffee shop

Latte art and a journal on a wood table by a sunlit window.

Try this preset

Food still life

Editorial food photography on a stone surface, soft side light.

Try this preset

Minimal poster

Editorial swiss-style poster with a single product silhouette.

Try this preset

Noir detective

1940s noir scene, hard shadows, cigarette smoke, cinematic.

Try this preset

Product on marble

Editorial product shot on a marble countertop, soft daylight from a window.

Try this preset

Sneaker product shot

High-end athletic sneaker on a clean podium with rim light.

Try this preset

Studio headshot

Clean corporate headshot, neutral grey backdrop, soft beauty light.

Try this preset

Tokyo streetstyle

Full-length editorial fashion shot, Tokyo back alley at dusk.

Try this preset

API Endpoint

POST

/api/v1/models/flux/run

LLM.txt

AI-Ready

For AI assistants

Copy this model's documentation into Claude, GPT, or any AI for instant integration help.

/llm/flux.txt

OpenAPI Spec

Swagger compatible

Import into Postman, Swagger UI, or generate client SDKs in any language.

/api/openapi

Parameters

Input parameters accepted by this model

Parameter	Type	Description	Default
`prompt` required	string	Text description of the image to generate	-
`model` required	string	FLUX variant identifier (e.g. "black-forest-labs/flux-dev", "black-forest-labs/flux-schnell", "black-forest-labs/flux-pro", "black-forest-labs/flux-1.1-pro", "black-forest-labs/flux-kontext-pro", "black-forest-labs/flux-kontext-max", "lucataco/hyper-flux-8step", "black-forest-labs/flux-schnell-lora", "black-forest-labs/flux-dev-lora").	-
`aspect_ratio`	enum	Image aspect ratio. Use "custom" with width/height for free-form sizes; "match_input_image" for image-to-image variants. `1:116:99:1621:99:21`+8 more	`1:1`
`num_outputs`	integer	How many images to generate per call. min: 1 \| max: 4	`1`
`seed`	integer	Random seed for reproducibility	-
`output_format`	string	Image output format	`png`
`output_quality`	integer	Output image quality (0–100, formats that support it). min: 0 \| max: 100	`80`
`guidance_scale`	number	Prompt adherence (variant-dependent).	-
`num_inference_steps`	integer	Number of denoising steps (variant-dependent).	-
`prompt_upsampling`	boolean	Enhance prompt for better results (Pro variants).	`false`
`safety_tolerance`	integer	Content filter strictness (1=strict, 5=permissive). Pro variants only. min: 1 \| max: 5	`5`
`width`	integer	Image width in pixels (used with aspect_ratio="custom").	-
`height`	integer	Image height in pixels (used with aspect_ratio="custom").	-
`megapixels`	string	Output resolution in megapixels (Schnell/Dev variants).	-
`hf_lora`	string	HuggingFace LoRA path or URL (e.g. "owner/repo" or a direct .safetensors URL). Only honored by LoRA-capable variants such as "black-forest-labs/flux-dev-lora" and "black-forest-labs/flux-schnell-lora".	-
`hf_loras`	array	Array of HuggingFace LoRA paths/URLs for stacked LoRA loading. items: string	-
`lora_weights`	string	URL or path to a single LoRA weights file (LoRA-capable variants only).	-
`lora_scale`	number	Strength of the LoRA effect (typical 0–2). min: -1 \| max: 3	`1`
`lora_scales`	array	Array of LoRA strengths matching hf_loras. items: number	-
`customLoras`	array	JSON array of custom LoRA objects. Each entry: {"modelUrl": "https://...", "scale": 1.0}. Resolved server-side; LoRA-capable variants only. items: string	-

Supported Aspect Ratios

1:1

16:9

9:16

21:9

9:21

3:2

2:3

4:5

5:4

3:4

4:3

Example Outputs

Real outputs generated by this model

View Details

high-end product photography, premium athletic sneaker centered on a minimal grey podium, dramatic rim light from above, clean white seamless background, advertising-grade composition

1 credits

7.1s

View Details

editorial food photography, plated dish on a textured stone surface, soft north-facing window light, dewy textures, michelin guide aesthetic, shallow depth of field

1 credits

7.1s

View Details

cinematic 1940s film noir scene, detective in fedora silhouetted by venetian blind shadows, cigarette smoke curling, hard chiaroscuro lighting, black and white with deep blacks

1 credits

3.9s

View Details

editorial fashion photograph, model in flowing linen against red rock desert at golden hour, wind catching the hair, kodak portra 400 grain, magazine cover quality

1 credits

6.8s

View Details

wide concert venue shot from the back of the crowd, performer silhouette against bright stage lights, sea of phones held up, lens flare, atmospheric haze, photojournalism style

1 credits

6.7s

View Details

editorial lifestyle photograph, latte with rosetta art beside an open journal on a worn wood table by a sunlit window, soft bokeh, warm tones, slow morning aesthetic

1 credits

6.7s

View Details

full-length editorial fashion photography, model in tokyo streetstyle outfit, narrow back alley at dusk, neon reflections, Kodak Portra 400 grain

1 credits

6.7s

View Details

professional studio headshot, neutral grey paper backdrop, soft beauty dish light, sharp eyes, subtle catch light, business-appropriate styling

1 credits

6.7s

View Details

editorial product photography, premium product centered on a marble countertop, soft north-facing window daylight, minimal styling, magazine-grade composition

1 credits

6.8s

View Details

minimal swiss-style editorial poster, single product silhouette, off-white background, oversized san-serif typography composition

1 credits

6.7s

View Details

modern architecture exterior at blue hour, long-exposure car light trails, mirrored glass facade, photorealistic, magazine cover composition

1 credits

6.7s

View Details

cinematic portrait, shallow depth of field, golden hour rim light, soft skin texture, color grade like A24

1 credits

6.7s

View Details

a thrilling action sequence of a woman trying to find her favorite candy. The candy wrapper is purple with a pixelated dragon and reads "Pixel Dojo". The woman says "Gotta have that pixel dojo candy. with over 60 ai tools, it's basically zero calories."

1 credits

6.6s

View Details

1 credits

6.8s

View Details

1 credits

6.6s

View Details

1 credits

3.7s

Code Examples

Copy and paste to get started

bash

curl -X POST "https://pixeldojo.ai/api/v1/models/flux/run" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A beautiful mountain landscape at golden hour",
    "aspect_ratio": "1:1"
  }'

Response Format

Submit Response (202 Accepted)

json

{
  "jobId": "job_abc123...",
  "status": "pending",
  "statusUrl": "https://pixeldojo.ai/api/v1/jobs/job_abc123...",
  "creditCost": 1,
  "creditsRemaining": 95,
  "expiresAt": "2025-01-23T12:00:00Z"
}

Completed Response

json

{
  "jobId": "job_abc123...",
  "status": "completed",
  "output": {
    "images": [
      "https://temp.pixeldojo.ai/pixeldojotemp/1705930123-456789.png"
    ]
  },
  "creditCost": 1,
  "expiresAt": "2025-01-23T12:00:00Z"
}

LLM Documentation Try in Web UI Get API Key Usage Dashboard Buy Credits

FLUX API

Get API Key

See Usage

Buy Credits

Try a preset

API Endpoint

LLM.txt

OpenAPI Spec

Parameters

Supported Aspect Ratios

See also

Example Outputs

Code Examples

Response Format

Submit Response (202 Accepted)

Completed Response