Flux Pulid

Flux Pulid

Playground

Try it on WavespeedAI!

FLUX-PuLID combines FLUX.1 [dev] with Personalized User Likeness ID (PuLID) technology, enabling high-quality personalized image generation from reference photos with exceptional realism and custom likenesses.

Features

⚡ FLUX-PuLID — Personalized Image Generation

FLUX-PuLID fuses the power of FLUX.1 [dev] with advanced Personalized User Likeness ID (PuLID) technology, enabling consistent character identity across different scenes, outfits, and artistic styles. Whether you want to turn a photo into a fantasy elf, cyberpunk warrior, or cinematic portrait, FLUX-PuLID ensures your face stays unmistakably you.


🎨 Why it looks great

  • 🧠 ID consistency: preserves facial structure, proportions, and expression across all generated images.
  • 👗 Flexible restyling: change outfits, lighting, or environment — from elegant fashion to sci-fi armor.
  • 🧝 Realistic transformations: morph your likeness into new worlds — elves, heroes, mecha pilots, or film characters.
  • 🎥 Cinematic detail: uses FLUX’s filmic rendering core for smooth tones, accurate skin, and realistic depth of field.
  • 🎭 Creative control: adjust guidance scale for balance between faithfulness and artistic freedom.

⚙️ Limits and Performance

  • Max resolution: up to 1536 × 1536 px
  • Input: image reference + descriptive prompt
  • Output formats: jpeg, png, webp

💰 Pricing

Each image costs $0.02.

TypePrice per Image
FLUX-PuLID$0.02

🚀 How to Use

  1. 🖼️ Upload a reference image — ensure the face in the image is clear and well-lit.
  2. ✍️ Write a descriptive prompt — specify the new style, outfit, or theme.
  3. 🎚️ Adjust settings — size, guidance scale, seed, and output format.
  4. ▶️ Click “Run” to generate your personalized image instantly.

💡 Pro Tips

  • Keep the face visible and well-lit in the input image for best likeness.
  • Use 3.0–4.0 guidance scale for natural balance between realism and creativity.
  • Try cinematic or fantasy prompts for striking artistic results.

🧾 Notes

Please double-check your image upload URL — if there’s an issue, the preview will not appear.

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/v3/wavespeed-ai/flux-krea-dev-lora" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1024*1024",
    "guidance_scale": 3.5,
    "seed": -1,
    "output_format": "jpeg",
    "enable_base64_output": false,
    "enable_sync_mode": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The positive prompt for the generation.
imagestringYes-
sizestringNo1024*1024256 ~ 1536 per dimensionThe size of the generated media in pixels (width*height).
guidance_scalenumberNo3.50.0 ~ 20.0The guidance scale to use for the generation.
seedintegerNo-1-1 ~ 2147483647The random seed to use for the generation. -1 means a random seed will be used.
output_formatstringNojpegjpeg, png, webpThe format of the output image.
enable_base64_outputbooleanNofalse-If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.
enable_sync_modebooleanNofalse-If set to true, the function will wait for the image to be generated and uploaded before returning the response. It allows you to get the image directly in the response. This property is only available through the API.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

© 2025 WaveSpeedAI. All rights reserved.