S2V 01 is MiniMax’s subject-reference video model. The supplied image guides a character’s appearance, while the text describes the video scene and action. Its documented reference type is a person’s face, so prepare the portrait as an identity guide for the character you want to place in the generated sequence.
Choose a reference in which the intended face is clear and easy to distinguish. Avoid hiding defining features behind a hand, a large accessory or a severe crop when those features matter to the result. Keep the portrait consistent across related shots so the source used to guide the character remains known. The reference provides appearance information; use the prompt to explain the scene the character should perform.
The maker’s subject-reference schema accepts one image in the reference-image array. Supported formats are JPG, JPEG, PNG and WebP, with a file size below 20 MB. The shorter side must exceed 300 pixels, and the aspect ratio must be between 2:5 and 5:2. Keep the exact image file with the generation record instead of substituting a different portrait during a later comparison.
Describe a scene with a clear role for the referenced person. For example, the character might walk into a quiet workshop, look at an object on the table and stop beside it. Specify the action, setting and viewpoint that matter to the finished shot. If the face needs to remain readable, plan the framing and movement around that requirement.
The text description supports up to 2,000 characters. Use those characters for concrete instructions: what the character does, what surrounds them and what the final view should show. Describe clothing or scene details when they are important to the story, then inspect how the generated video combines them with the supplied identity reference. Keep the reference role distinct from a request to reproduce the portrait’s entire background as an opening frame.
Automatic prompt optimization is documented and enabled by default. It can be disabled when closer control of the written description is needed. Preserve that choice with the text and portrait when comparing different scenes. To investigate a likeness issue, keep the scene brief constant while comparing an improved reference; to investigate the action, keep the reference constant while revising the motion description.
The maker’s workflow returns a task identity before the video is complete. Keep that original identity through the status and result steps, then save the completed clip for inspection and editing. Retain the portrait, prompt and resulting video as one record so a later shot can be compared with the actual material that guided the earlier result.
Review the character throughout the sequence, including turns, gestures and changes in framing. Check facial consistency, the readability of the intended action and the relationship between the character and scene objects. Select the clip that best serves the shot’s purpose, and identify any concrete mismatch before revising the input. A recurring character workflow benefits from reviewing several finished shots side by side, using the same portrait reference and a clear record of each scene description.
", "aboutText": "S2V 01 is MiniMax’s subject-reference video model. The supplied image guides a character’s appearance, while the text describes the video scene and action. Its documented reference type is a person’s face, so prepare the portrait as an identity guide for the character you want to place in the generated sequence.\n\nChoose a reference in which the intended face is clear and easy to distinguish. Avoid hiding defining features behind a hand, a large accessory or a severe crop when those features matter to the result. Keep the portrait consistent across related shots so the source used to guide the character remains known. The reference provides appearance information; use the prompt to explain the scene the character should perform.\n\nThe maker’s subject-reference schema accepts one image in the reference-image array. Supported formats are JPG, JPEG, PNG and WebP, with a file size below 20 MB. The shorter side must exceed 300 pixels, and the aspect ratio must be between 2:5 and 5:2. Keep the exact image file with the generation record instead of substituting a different portrait during a later comparison.\n\nDescribe a scene with a clear role for the referenced person. For example, the character might walk into a quiet workshop, look at an object on the table and stop beside it. Specify the action, setting and viewpoint that matter to the finished shot. If the face needs to remain readable, plan the framing and movement around that requirement.\n\nThe text description supports up to 2,000 characters. Use those characters for concrete instructions: what the character does, what surrounds them and what the final view should show. Describe clothing or scene details when they are important to the story, then inspect how the generated video combines them with the supplied identity reference. Keep the reference role distinct from a request to reproduce the portrait’s entire background as an opening frame.\n\nAutomatic prompt optimization is documented and enabled by default. It can be disabled when closer control of the written description is needed. Preserve that choice with the text and portrait when comparing different scenes. To investigate a likeness issue, keep the scene brief constant while comparing an improved reference; to investigate the action, keep the reference constant while revising the motion description.\n\nThe maker’s workflow returns a task identity before the video is complete. Keep that original identity through the status and result steps, then save the completed clip for inspection and editing. Retain the portrait, prompt and resulting video as one record so a later shot can be compared with the actual material that guided the earlier result.\n\nReview the character throughout the sequence, including turns, gestures and changes in framing. Check facial consistency, the readability of the intended action and the relationship between the character and scene objects. Select the clip that best serves the shot’s purpose, and identify any concrete mismatch before revising the input. A recurring character workflow benefits from reviewing several finished shots side by side, using the same portrait reference and a clear record of each scene description.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "29b238eaae88b431656b0feb89bcb8fda0a3f7f6cf445e387bed0d3fdfac0cac", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "minimaxi-s2v-01S2V 01 uses a portrait reference to guide a character in a newly generated video. Supply one clear face image and describe the scene and action; the maker’s subject-reference workflow treats the image as a character reference.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
S2V 01 is MiniMax’s subject-reference video model. The supplied image guides a character’s appearance, while the text describes the video scene and action. Its documented reference type is a person’s face, so prepare the portrait as an identity guide for the character you want to place in the generated sequence.
Choose a reference in which the intended face is clear and easy to distinguish. Avoid hiding defining features behind a hand, a large accessory or a severe crop when those features matter to the result. Keep the portrait consistent across related shots so the source used to guide the character remains known. The reference provides appearance information; use the prompt to explain the scene the character should perform.
The maker’s subject-reference schema accepts one image in the reference-image array. Supported formats are JPG, JPEG, PNG and WebP, with a file size below 20 MB. The shorter side must exceed 300 pixels, and the aspect ratio must be between 2:5 and 5:2. Keep the exact image file with the generation record instead of substituting a different portrait during a later comparison.
Describe a scene with a clear role for the referenced person. For example, the character might walk into a quiet workshop, look at an object on the table and stop beside it. Specify the action, setting and viewpoint that matter to the finished shot. If the face needs to remain readable, plan the framing and movement around that requirement.
The text description supports up to 2,000 characters. Use those characters for concrete instructions: what the character does, what surrounds them and what the final view should show. Describe clothing or scene details when they are important to the story, then inspect how the generated video combines them with the supplied identity reference. Keep the reference role distinct from a request to reproduce the portrait’s entire background as an opening frame.
Automatic prompt optimization is documented and enabled by default. It can be disabled when closer control of the written description is needed. Preserve that choice with the text and portrait when comparing different scenes. To investigate a likeness issue, keep the scene brief constant while comparing an improved reference; to investigate the action, keep the reference constant while revising the motion description.
The maker’s workflow returns a task identity before the video is complete. Keep that original identity through the status and result steps, then save the completed clip for inspection and editing. Retain the portrait, prompt and resulting video as one record so a later shot can be compared with the actual material that guided the earlier result.
Review the character throughout the sequence, including turns, gestures and changes in framing. Check facial consistency, the readability of the intended action and the relationship between the character and scene objects. Select the clip that best serves the shot’s purpose, and identify any concrete mismatch before revising the input. A recurring character workflow benefits from reviewing several finished shots side by side, using the same portrait reference and a clear record of each scene description.
POST /v1/videostext, imagevideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits minimaxi-s2v-01 Conditions: Use the exact Ailoot model selector. | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Conditions: Describe the scene and motion. | Default— |
Fieldend_image | Typestring | RequirementOptional | Values & limits Conditions: An end frame applies only in a supported image input mode. | Default— |
Fieldimage | Typestring or array<string> | RequirementOptional | Values & limits Conditions: Use an actual publicly reachable image URL or a base64 image string; no maximum image count is asserted here. | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parameteroptional | Contractend_image, image |
Parametermaterial_types | Contracttext, image |
Parameterconditions | ContractUse the exact Ailoot model selector., Describe the scene and motion., An end frame applies only in a supported image input mode., Use an actual publicly reachable image URL or a base64 image string; no maximum image count is asserted here. |
Method aliases: /v1/videos/generations
Lifecycle: submit_once_poll_original
GET /v1/videos/{request_id}
GET /v1/videos/generations/{request_id}
GET /v1/videos/{request_id}/content
GET /v1/media/assets
GET /v1/media/assets/{asset_id}
The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Forecast quantity | Billing quantity | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Billing quantity— | Charge Input · Input tokens · Estimate for comparison only — / 1K tokens Output · Output tokens · Estimate for comparison only — / 1K tokens Input · Cache read · Estimate for comparison only — / 1K tokens Input · Cache write · Estimate for comparison only — / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only — / 1K tokens |
| ConfigurationPer request | Rate schedule— | Forecast quantity— | Billing quantityone request | Charge Input · Estimate for comparison only $1.4 per request |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Billing quantity— | Charge Output · Estimated generation cost · Estimate for comparison only $1.4 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
# Replace YOUR_ACCESSIBLE_IMAGE_URL with your actual reachable reference image URL.\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncat > request.json <<'JSON'\n{\n "model": "minimaxi-s2v-01",\n "prompt": "A cat is walking on grass.",\n "image": "YOUR_ACCESSIBLE_IMAGE_URL"\n}\nJSON\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Create once; retain id, polling_url, original task identifiers and every header.\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_STATUS'\nimport json,os,subprocess\nfrom pathlib import Path\nfrom urllib.parse import urljoin,urlsplit\nr=json.loads(Path("result.json").read_text())\nu=urljoin("https://api.ailoot.ai",r["polling_url"])\np=urlsplit(u)\nif p.scheme!="https" or p.netloc!="api.ailoot.ai" or p.username or p.password:\n raise SystemExit("Unexpected returned polling URL; preserve the response")\nsubprocess.run(["curl","--fail-with-body","--silent","--show-error",u,"-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"],"-D","status-headers.txt","-o","status.json"],check=True)\n# Read this same original polling_url again while pending.\n# Preserve unknown/result_pending_check; do not repeat creation.\nPY_STATUS\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_ASSETS'\nimport json,os,subprocess\nfrom pathlib import Path\nfrom urllib.parse import urljoin,urlsplit\nr=json.loads(Path("status.json").read_text())\nroles={}\ndef visit(v,path=""):\n if isinstance(v,dict):\n for k,x in v.items(): visit(x,path+"/"+k)\n elif isinstance(v,list):\n for i,x in enumerate(v): visit(x,path+"/"+str(i))\n elif isinstance(v,str):\n u=urljoin("https://api.ailoot.ai",v); p=urlsplit(u)\n if p.scheme=="https" and p.netloc=="api.ailoot.ai" and not p.username and not p.password and p.path.startswith("/v1/media/assets/") and p.path.endswith("/content"):\n roles.setdefault(u,[]).append(path)\nvisit(r)\nif not roles: raise SystemExit("No completed owned assets; retain the original status")\nmanifest=[]\nfor i,(u,paths) in enumerate(roles.items()):\n target=Path(f"asset-{i}.bin")\n subprocess.run(["curl","--fail-with-body","--silent","--show-error",u,"-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"],"-o",str(target)],check=True)\n raw=target.read_bytes()\n if not raw: raise SystemExit("Empty asset; retain original status and metadata")\n ext="glb" if raw[:4]==b"glTF" else "png" if raw[:8]==b"\\x89PNG\\r\\n\\x1a\\n" else "jpg" if raw[:3]==b"\\xff\\xd8\\xff" else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "mp4" if raw[4:8]==b"ftyp" else "bin"\n name=f"asset-{i}.{ext}"\n if target.name!=name: target.rename(name)\n manifest.append({"file":name,"response_paths":paths,"bytes":len(raw)})\nPath("asset-manifest.json").write_text(json.dumps(manifest,indent=2))\nprint("Saved",len(manifest),"unique owned assets; every response role retained")\nPY_ASSETS\nGET /v1/videos/{request_id}GET /v1/videos/generations/{request_id}GET /v1/videos/{request_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}Save every completed video or returned file; retrieve every actual returned asset URL.
Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.
Keep the returned public task or operation id and all headers. Read only the original task; unknown or result_pending_check does not authorize another creation.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldpolling_url | Typestring |
Fieldprovider_task_id | Typestring |
Fieldtask_id | Typestring |
Fieldstatus | Typestring |
Fieldvideo_url | Typestring |
Ailoot Ultra minimaxi-s2v-01
/v1/videos/generations