FLUX-PuLID uses FLUX.1 [dev] and PuLID to create photorealistic images from reference photos that preserve custom likenesses. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.02per run·~50 / $1
ExamplesView all
A perfect detailed photo of a woman in high-tech battle armor, covering her face with her hands, shallow depth of field, cinematic lighting, glowing neon accents on armor, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, intricate design, futuristic, film grain, grainy
a woman holding sign with glowing green text \"PuLID for FLUX\"
portrait, side view
portrait of (white-haired:1.1) celebritygirl, wearing lacoste royal-blue sweater
woman with vr technology atmosphere revolutionary exceptional magnum with remarkable details
A perfect detailed photo of a woman covering her face with her hands, shallow depth of field, vignette, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, film grain, grainy
a young child is eating Icecream.
portrait, Chinese ink painting style
portrait, made of ice sculpture
portrait, candle light
portrait, sticker art
A perfect detailed photo of a woman in a stylish bikini, shallow depth of field, cinematic lighting, beach environment, highly detailed, high budget, bokeh, cinemascope, moody, epic, gorgeous, summer vibes, film grain, grainy
Related Models
README
⚡ 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.
| Type | Price per Image |
|---|---|
| FLUX-PuLID | $0.02 |
🚀 How to Use
- 🖼️ Upload a reference image — ensure the face in the image is clear and well-lit.
- ✍️ Write a descriptive prompt — specify the new style, outfit, or theme.
- 🎚️ Adjust settings — size, guidance scale, seed, and output format.
- ▶️ 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.
Flux Pulid API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-krea-dev-lora with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Flux Pulid below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-krea-dev-lora" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"size": "1024*1024",
"guidance_scale": 3.5,
"seed": -1,
"output_format": "jpeg",
"enable_base64_output": false,
"enable_sync_mode": false
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("wavespeed-ai/flux-pulid", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"size": "1024*1024",
"guidance_scale": 3.5,
"seed": -1,
"output_format": "jpeg",
"enable_base64_output": false,
"enable_sync_mode": false
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/flux-pulid",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://example.com/your-input.jpg",
"size": "1024*1024",
"guidance_scale": 3.5,
"seed": -1,
"output_format": "jpeg",
"enable_base64_output": false,
"enable_sync_mode": false
}
)
print(output["outputs"][0]) # → URL of the generated outputFlux Pulid API — Frequently asked questions
What is the Flux Pulid API?
Flux Pulid is a WaveSpeedAI model for image editing, exposed as a REST API on WaveSpeedAI. FLUX-PuLID uses FLUX.1 [dev] and PuLID to create photorealistic images from reference photos that preserve custom likenesses. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Flux Pulid API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/flux-pulid.
How much does Flux Pulid cost per run?
Flux Pulid starts at $0.020 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Flux Pulid accept?
Key inputs: `prompt`, `image`, `size`, `seed`, `guidance_scale`, `enable_base64_output`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/flux-pulid.
How long does Flux Pulid take to generate?
Average end-to-end generation time on WaveSpeedAI is around 54 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Flux Pulid outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.