by 0G Foundation
Async image editing model supporting multimodal input (image and text) for targeted visual modifications.
2K
2,048 tokens
—
0.0050 0G
per image
—
N/A for image
Async API — Image editing uses an asynchronous flow: submit a job, then poll for the result. The examples below show both steps.
# 1. Submit async image edit job (multipart/form-data)
curl https://router-api-testnet.integratenetwork.work/v1/async/images/edits \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-F model="qwen-image-edit" \
-F prompt="Make the sky purple" \
-F image="@input.png" \
-F n=1 \
-F size="1024x1024" \
-F response_format="b64_json"
# Response: {"jobId": "abc123", "status": "pending", "provider_address": "0x..."}
# 2. Poll for result (repeat until status is "completed")
curl "https://router-api-testnet.integratenetwork.work/v1/async/jobs/<JOB_ID>?provider_address=<PROVIDER_ADDRESS>&model=qwen-image-edit" \
-H "Authorization: Bearer <YOUR_API_KEY>"TEE Verification
Request on-chain signature verification with verify_tee. The response includes a tee_verified field in the trace.
# Add verify_tee as a query parameter (multipart requests)
curl "https://router-api-testnet.integratenetwork.work/v1/async/images/edits?verify_tee=true" \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-F model="qwen-image-edit" \
-F prompt="Make the sky purple" \
-F image="@input.png"
# Then poll with verify_tee query param
curl "https://router-api-testnet.integratenetwork.work/v1/async/jobs/<JOB_ID>?provider_address=<ADDR>&model=qwen-image-edit&verify_tee=true" \
-H "Authorization: Bearer <YOUR_API_KEY>"Private models only
This model is Private. To pin requests to a TEE-backed provider, add the X-0G-Provider-Trust-Mode: private header. Opt-in — not applied by default.
X-0G-Provider-Trust-Mode: private