SDXL
ControlNetXL (CNXL) - Huchenlei-PuLID
model_id: controlnetxl-cnxl-huchenlei-pulid
PuLID is an ip-adapter alike method to restore facial identity. It uses both insightface embedding and CLIP embedding similar to what ip-adapter faceid plus model does. However, there is an extra process of masking out the face from background environment using facexlib before passing image to CLIP. PuLID is an ip-adapter alike method to restore facial identity. It uses both insightface embedding and CLIP embedding similar to what ip-adapter faceid plus model does. However, there is an extra process of masking out the face from background environment using facexlib before passing image to CLIP. You can integrate ControlNetXL (CNXL) - Huchenlei-PuLID into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "controlnetxl-cnxl-huchenlei-pulid" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ControlNetXL (CNXL) - Huchenlei-PuLID costs $0.0047 per API call. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started.
Generate with ControlNetXL (CNXL) - Huchenlei-PuLID via API
Send a POST request to https://stablediffusionapi.com/api/v4/dreambooth with your API key.
Get yours at modelslab.com.
curl -X POST 'https://stablediffusionapi.com/api/v4/dreambooth' \
-H 'Content-Type: application/json' \
-d '{
"key": "YOUR_API_KEY",
"model_id": "controlnetxl-cnxl-huchenlei-pulid",
"prompt": "a photo of controlnetxl (cnxl) - huchenlei-pulid",
"negative_prompt": null,
"width": "512",
"height": "512",
"samples": "1",
"num_inference_steps": "30",
"guidance_scale": "7.5",
"safety_checker": "no",
"enhance_prompt": "yes",
"seed": null,
"webhook": null,
"track_id": null
}' Parameters
| Parameter | Default | Description |
|---|---|---|
| model_id | controlnetxl-cnxl-huchenlei-pulid | Model identifier |
| prompt | ||
| negative_prompt | ||
| width | 512 | Output image width (px) |
| height | 512 | Output image height (px) |
| samples | 1 | Number of images to generate |
| num_inference_steps | 30 | Denoising steps (1-50) |
| guidance_scale | 7.5 | Prompt adherence (1-20) |
| seed | null | Random seed (null to randomize) |
| safety_checker | yes | NSFW filter (yes/no) |
| enhance_prompt | yes | Auto-improve prompt (yes/no) |
Also searched as
ControlNetXL (CNXL) - Huchenlei-PuLID is also known as: ControlNetXL (CNXL) - Huchenlei-PuLID, controlnetxl-cnxl-huchenlei-pulid, controlnetxl cnxl huchenlei pulid, controlnetxlcnxlhuchenleipulid, controlnetxl.cnxl.huchenlei.pulid. Use it for sdxl image generation, available for download via the Stable Diffusion API REST API at https://stablediffusionapi.com/api/v4/dreambooth.
FAQ — ControlNetXL (CNXL) - Huchenlei-PuLID
- How do I use ControlNetXL (CNXL) - Huchenlei-PuLID via API?
- Send a POST request to https://stablediffusionapi.com/api/v4/dreambooth with your API key, prompt, and model_id "controlnetxl-cnxl-huchenlei-pulid". Get an API key from modelslab.com.
- Is ControlNetXL (CNXL) - Huchenlei-PuLID free to use?
- Yes — Stable Diffusion API offers a free tier with 20 generations. Paid plans starting at $8/month give you unlimited access to ControlNetXL (CNXL) - Huchenlei-PuLID and 1,000+ other models.
- What parameters does ControlNetXL (CNXL) - Huchenlei-PuLID support?
- ControlNetXL (CNXL) - Huchenlei-PuLID accepts standard Stable Diffusion parameters: prompt, negative_prompt, width, height, samples, num_inference_steps (default 30), guidance_scale (default 7.5), seed, and safety_checker.
- Can I use generated images commercially?
- Yes. You retain copyright on all images you generate via the API and can use them commercially.
Related models
Controlnetxl Cnxl Tencentarc Openpose
378.1K images generated
Cyberreal
378.1K images generated
Gakuen De Jikan Yo Tomare AnimagineXL 4 0opt 1754375412
378.1K images generated
Stable Diffusion v1-5
Nudify V141
378.1K images generated
Deliberate V2
378.1K images generated
Realistic Vision V51
378.1K images generated
Anything V5
378.1K images generated