SOUL is a realistic image-to-image engine for sophisticated visuals that, with Soul ID, preserves character consistency across scenes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
就绪

$0.09每次运行·~11 / $1
Higgsfield SOUL Image-to-Image is a high-quality image transformation model built for realism, tasteful aesthetics, and strong character consistency. It is designed for reference-driven image editing workflows where you want to restyle, reframe, or evolve a subject while preserving identity, structure, and visual coherence.
Elegant realism Produce believable lighting, natural skin and hair, and clean material rendering without an over-processed look.
Strong character consistency Keep the same identity across different scenes, poses, outfits, and lighting conditions.
Faithful image-to-image editing Preserve core composition and structure while changing styling, color, mood, wardrobe, or background.
Art-direction friendly Respond well to cinematic language such as lens cues, depth of field, rim light, palette direction, and grading intent.
Wide stylistic range Move between photoreal, editorial, painterly, or graphic looks without heavy prompt engineering.
| Parameter | Required | Description |
|---|---|---|
| image | Yes | Reference image used as the source for the transformation. |
| prompt | Yes | Text instruction describing the desired transformation, style, setting, mood, or visual direction. |
| quality | No | Output quality tier. Supported values: medium, high. |
| aspect_ratio | No | Output aspect ratio for the generated image. |
| strength | No | Controls how closely the result follows the source image versus allowing freer restyling. |
medium for lower cost or high for stronger final quality.Turn this portrait into a cinematic editorial fashion shot at golden hour, soft rim light, clean skin texture, natural color grading, luxury wardrobe styling, realistic background depth
Pricing depends on the selected quality tier.
| Quality | Price per Image |
|---|---|
| Medium | $0.09 |
| High | $0.19 |
medium costs $0.09 per imagehigh costs $0.19 per imagesoul_id when building a sequence or visual set around the same subject.strength when structure fidelity matters more than style variation.high quality for final selects and medium when exploring directions more quickly.soul_id can improve continuity across generations.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/higgsfield/soul/image-to-image with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Soul Image To Image below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"size": "1152*2048",
"style": "Creatures",
"strength": 1,
"quality": "medium"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/higgsfield/soul/image-to-image" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/higgsfield/soul/image-to-image";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"size": "1152*2048",
"style": "Creatures",
"strength": 1,
"quality": "medium"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"size": "1152*2048",
"style": "Creatures",
"strength": 1,
"quality": "medium"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/higgsfield/soul/image-to-image", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Soul Image To Image is a Higgsfield model for image editing, exposed as a REST API on WaveSpeedAI. SOUL is a realistic image-to-image engine for sophisticated visuals that, with Soul ID, preserves character consistency across scenes. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/higgsfield/higgsfield-soul-image-to-image.
Soul Image To Image starts at $0.090 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.
Key inputs: `prompt`, `image`, `size`, `seed`, `quality`, `strength`. 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/higgsfield/higgsfield-soul-image-to-image.
Median end-to-end generation time on WaveSpeedAI is around 104 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Higgsfield). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.