Picsart API Platform
← All models

Picsart Angle Change

Picsart · Image · Image → Image

Change the camera angle / viewpoint of a subject with automatic relighting.

Model ID: picsart-qwen-image-edit-angleWorkflow: pcp/v1/qwen-image-edit-angle
Image InputMulti-Ref
Try on Playground ↗
SDKAPIAdvanced UsagePricing

Overview

Alongside the unified model APIs, we expose compatibility APIs that take each vendor's original parameters exactly as the vendor defines them — nothing renamed, nothing reshaped on the way through.

That makes them the shortest path onto Picsart if you already work with the vendor directly: the request bodies you've already written keep working as they are. You keep their parameter names and defaults, and you get the vendor's full parameter set rather than the subset that is shared across every model.

The cost is that a request is written for one vendor — switching models later means rewriting it, and results come back in the vendor's own shape. When you'd rather write once and change models freely, use the unified API.

Make a request

Call the workflow with ai.apis.run() in TypeScript, or hit /workflows/{workflow}/execute directly — params is passed through untouched either way.

These endpoints are addressed by workflow name rather than model id: the one in this model's header, since one model runs as one workflow. Authentication is unchanged — your Picsart API key as a bearer token (see Authentication).

ts
import { createClient, ApiRunMode } from '@picsart/ai-sdk';

const ai = createClient({
  apiKey: process.env.PICSART_API_KEY,
  apiUrl: 'https://api.picsart.com',
});

// Calls the 'pcp/v1/qwen-image-edit-angle' workflow directly — params are sent as-is.
const { result, usage } = await ai.apis.run('pcp/v1/qwen-image-edit-angle', {
  image: "your value here",
  prompt: "A serene mountain lake at golden hour, ultra detailed"
}, {
  mode: ApiRunMode.SYNC,
});

console.log(result); // workflow-specific output
console.log(usage?.credits); // credits charged

Parameters

14 parameters, sent inside params. These are the vendor's own names, so they line up one-for-one with the vendor's documentation. Required ones must be supplied; the rest fall back to their defaults.

ParameterTypeRequiredDefaultDetails
image
URL of the input image, or an array of URLs. The first image is the main reference; additional images can be referenced as Picture 1, Picture 2, etc. in the prompt.
string | arrayyes——
prompt
Positive prompt describing what should appear in the output image.
stringno——
system_prompt
System prompt steering the editing behavior.
stringno——
negative_prompt
Negative prompt describing what should NOT appear in the output image.
stringno——
strength
Denoising strength of the image-to-image pipeline. Larger values produce more creative results with possibly less fidelity.
numberno——
grag_scale
Grag scale for fine-grained control over editing strength. 1 disables the grag scale; larger values preserve more fidelity and reduce editing.
numberno——
drop_cond_tokens_prob
Probability of dropping conditioning tokens. 0 means no tokens are dropped.
numberno——
seed
Random seed for reproducibility. Use -1 to generate a random seed on each call.
numberno——
output_format
Output image format. If omitted, the format is preserved from the input image.
stringno—
JPEGPNGHEICWEBP
options
Options controlling safety checks and drive integration.
objectno——
└safety_checks
Safety check settings
objectno——
└enabled
Whether to run content moderation. Defaults to true.
booleanno——
└drive
Save result to Picsart Drive
objectno——
└name
File name in Picsart Drive
stringyes——
└attributes
Custom attributes to attach to the file
objectno——
└folder
Target folder in Picsart Drive
objectno——
model
Qwen Image Edit Angle model variant to use. Defaults to the stable release.
stringno—
preview-model-qwent-image-edit-anglemodel-qwent-image-edit-angle
lora_params
LoRA parameters. If omitted, the angle + lighting LoRAs are applied automatically.
objectno——
└lora_weights
LoRA adapter weights keyed by adapter name. Defaults to { lora_angle: 1, lora_angle_lighting: 1 } when omitted.
objectno—
e.g. {"lora_angle":1,"lora_angle_lighting":1}
└keep_other_weights
If false (default), adapters not listed in lora_weights are set to 0.
booleanno——
num_inference_steps
Number of inference steps. Defaults to 16.
numberno——
guidance_scale
Guidance scale. Defaults to 4.
numberno——

Response

Over HTTP the output arrives inside a status envelope, at response.result. ai.apis.run() unwraps that envelope for you and resolves to { result, usage } instead. Either way the resultitself is the vendor's own shape.

json
{
  "result": {
    "url": "https://cdn.picsart.com/…/result.jpg",
    "mimeType": "image/jpeg",
    "driveFile": {}
  },
  "usage": {
    "credits": 4
  }
}