HappyHorse-1.1-R2V creates a new video scene from reference images and a text prompt. Alibaba designs the model to preserve recognizable characters, objects and visual style while generating movement. The references establish the scene's content and appearance, and the text describes how those elements should interact.
Between one and nine images can be used. They may define a character, an object, the surroundings or an artistic treatment. The prompt can identify a reference by number and name a particular object in it, linking the visual material to the relevant part of the action. This is especially useful when elements from several images need to be combined in one composition.
Unlike the mode that uses an initial frame, references here guide the content of a new scene. A text prompt is required: it connects the appearance of objects to the action, camera movement and overall staging. The manufacturer highlights visual consistency and cinematic movement. The model generates a new video rather than editing the source images.
JPEG, JPG, PNG and WEBP files of up to 20 MB each are accepted. The shorter dimension must be at least 400 pixels; material at 720P or higher is recommended. This mode takes images and text as its inputs.
The result is saved as MP4 at 24 frames per second. Duration is specified as an integer from 3 to 15 seconds. Resolution can be selected from 480P, 720P and 1080P; audio generation is supported.
Landscape, portrait and square frames are available: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21 and 21:9. Selecting a format helps define the compositional space of the new scene in advance.
The prompt may be in any language. The limit is 5000 non-Chinese or 2500 Chinese characters, with any excess truncated. The most important reference roles, actions and movements must fit within this length. A random seed can guide similarity between variations, but does not guarantee an exact reproduction of a video.
", "aboutText": "HappyHorse-1.1-R2V creates a new video scene from reference images and a text prompt. Alibaba designs the model to preserve recognizable characters, objects and visual style while generating movement. The references establish the scene's content and appearance, and the text describes how those elements should interact.\n\n### The roles of visual references\n\nBetween one and nine images can be used. They may define a character, an object, the surroundings or an artistic treatment. The prompt can identify a reference by number and name a particular object in it, linking the visual material to the relevant part of the action. This is especially useful when elements from several images need to be combined in one composition.\n\nUnlike the mode that uses an initial frame, references here guide the content of a new scene. A text prompt is required: it connects the appearance of objects to the action, camera movement and overall staging. The manufacturer highlights visual consistency and cinematic movement. The model generates a new video rather than editing the source images.\n\nJPEG, JPG, PNG and WEBP files of up to 20 MB each are accepted. The shorter dimension must be at least 400 pixels; material at 720P or higher is recommended. This mode takes images and text as its inputs.\n\n### Duration, framing and audio\n\nThe result is saved as MP4 at 24 frames per second. Duration is specified as an integer from 3 to 15 seconds. Resolution can be selected from 480P, 720P and 1080P; audio generation is supported.\n\nLandscape, portrait and square frames are available: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21 and 21:9. Selecting a format helps define the compositional space of the new scene in advance.\n\nThe prompt may be in any language. The limit is 5000 non-Chinese or 2500 Chinese characters, with any excess truncated. The most important reference roles, actions and movements must fit within this length. A random seed can guide similarity between variations, but does not guarantee an exact reproduction of a video.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "8b872e3a4e3a48939f0f854b95b713e8a4a01a1a14ceac31b0921c4b2d97390f", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "happyhorse-1.1-r2vA video generation model driven by reference images and a text scenario. Helps preserve the appearance of characters, objects and the visual style in a new scene.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
HappyHorse-1.1-R2V creates a new video scene from reference images and a text prompt. Alibaba designs the model to preserve recognizable characters, objects and visual style while generating movement. The references establish the scene's content and appearance, and the text describes how those elements should interact.
Between one and nine images can be used. They may define a character, an object, the surroundings or an artistic treatment. The prompt can identify a reference by number and name a particular object in it, linking the visual material to the relevant part of the action. This is especially useful when elements from several images need to be combined in one composition.
Unlike the mode that uses an initial frame, references here guide the content of a new scene. A text prompt is required: it connects the appearance of objects to the action, camera movement and overall staging. The manufacturer highlights visual consistency and cinematic movement. The model generates a new video rather than editing the source images.
JPEG, JPG, PNG and WEBP files of up to 20 MB each are accepted. The shorter dimension must be at least 400 pixels; material at 720P or higher is recommended. This mode takes images and text as its inputs.
The result is saved as MP4 at 24 frames per second. Duration is specified as an integer from 3 to 15 seconds. Resolution can be selected from 480P, 720P and 1080P; audio generation is supported.
Landscape, portrait and square frames are available: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21 and 21:9. Selecting a format helps define the compositional space of the new scene in advance.
The prompt may be in any language. The limit is 5000 non-Chinese or 2500 Chinese characters, with any excess truncated. The most important reference roles, actions and movements must fit within this length. A random seed can guide similarity between variations, but does not guarantee an exact reproduction of a video.
POST /v1/videos/generationstext, imagevideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits happyhorse-1.1-r2v | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldduration | Typeinteger | RequirementOptional | Values & limits Minimum: 3 Maximum: 15 Unit: seconds | Default5 |
Fieldresolution | Typestring | RequirementOptional | Values & limits 480P, 720P, 1080P | Default720P |
Fieldratio | Typestring | RequirementOptional | Values & limits 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9 | Default16:9 |
Fieldimage_urls | Typehttps_url|data_image_url[] | RequirementRequired | Values & limits Minimum items: 1 Maximum items: 9 Maximum decoded bytes: 20,971,520 MIME types: image/jpeg, image/png, image/webp | Default— |
reference_images_to_video · Required: prompt, image_urls
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt, image_urls |
Parametermaterial_types | Contracttext, image |
Parameteroptional | Contractduration, resolution, ratio |
Parameterduration_integer_range | Contract3, 15 |
Parameterdefault_duration | Contract5 |
Parameterresolution | Contract480P, 720P, 1080P |
Parameterdefault_resolution | Contract720P |
Parameterratio | Contract16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9 |
Parameterratio_must_omit | Contractfalse |
Parameterimage_urls | Contract{"min_count":1,"max_count":9,"schemes":["https","data raster base64"],"max_data_image_bytes":20971520} |
Lifecycle: submit_once_poll_original
GET /v1/videos/{request_id}
GET /v1/videos/generations/{request_id}
GET /v1/videos/{request_id}/content
GET /v1/videos/generations/{request_id}/content
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/videos/generationsAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_URLS_FILE:?Set a JSON file containing your actual reference-image URLs}"\nexport AILOOT_IMAGE_URLS_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "happyhorse-1.1-r2v", "prompt": "The subject walks slowly toward the camera.", "duration": 5, "resolution": "720P"}')\nfrom urllib.parse import urlsplit\nf=Path(os.environ["AILOOT_IMAGE_URLS_FILE"])\nif not f.is_file():raise SystemExit("Choose the actual reference URL JSON file")\nurls=json.loads(f.read_text())\nif not isinstance(urls,list) or not 1<=len(urls)<=9:raise SystemExit("Provide one to nine reference-image URLs")\nfor u in urls:\n z=urlsplit(u) if isinstance(u,str) else None\n if not z or z.scheme!="https" or not z.netloc or z.username or z.password:raise SystemExit("Each reference must be an actual HTTPS image URL")\np["image_urls"]=urls\np["ratio"]="16:9"\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nprint(json.dumps(r))\nPY_RESULT\nmp4
GET /v1/videos/{request_id}GET /v1/videos/generations/{request_id}GET /v1/videos/{request_id}/contentGET /v1/videos/generations/{request_id}/contentset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_OPERATION_ID:?Set the actual Ailoot operation ID returned by creation}"\nexport AILOOT_OPERATION_ID\noperation_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ["AILOOT_OPERATION_ID"],safe=""))')\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/videos/generations/$operation_id" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o status.json\npython3 - <<'PY_STATUS'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("status.json").read_text())\nprint(json.dumps(r))\nif r.get("status")=="completed":\n for x in r.get("data",[]):print(x)\nPY_STATUS\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_STATUS_FILE:?Set the actual completed status JSON file}"\nexport AILOOT_STATUS_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nfrom urllib.parse import urlsplit,urljoin\nf=Path(os.environ["AILOOT_STATUS_FILE"])\nif not f.is_file():raise SystemExit("Choose the actual completed status file")\nr=json.loads(f.read_text())\nif r.get("status")!="completed" or not isinstance(r.get("data"),list) or not r["data"]:raise SystemExit("Wait for a completed status with asset paths")\nurls=[]\nfor x in r["data"]:\n if not isinstance(x,str) or "\\n" in x or "\\r" in x:raise SystemExit("Invalid asset path")\n u=urljoin("https://api.ailoot.ai",x)\n z=urlsplit(u)\n if z.scheme!="https" or z.netloc!="api.ailoot.ai" or z.username or z.password:raise SystemExit("Use the actual Ailoot asset paths from status")\n urls.append(u)\nPath("asset-urls.txt").write_text("\\n".join(urls)+"\\n")\nPY_REQUEST\nindex=0\nwhile IFS= read -r asset_url; do\n curl --fail-with-body --silent --show-error "$asset_url" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o "video-${index}.mp4"\n index=$((index + 1))\ndone < asset-urls.txt\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_OPERATION_ID:?Set the actual Ailoot operation ID returned by creation}"\nexport AILOOT_OPERATION_ID\noperation_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ["AILOOT_OPERATION_ID"],safe=""))')\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/videos/generations/$operation_id/content" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o video.mp4\nSave every completed video or returned file; retrieve every actual returned asset URL.
Preserve every returned data item/output index. content_url is first only; fetch every actual content path/asset. GETcontentwithoutindex isnotalloutputs.
Read existing original job; never resubmit unknown send.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldobject | Typestring |
Fieldmodel | Typestring |
Fieldstatus | Typestring |
Fieldcontent_url | Typesigned URL |
Fielddata[] | Typesigned URL |
Fieldusage | Typeobject |
Fieldresult_pending_check | Typeboolean |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Response409 · video_not_ready | ConditionOriginal result content is not yet available | Next stepPoll the original returned ID and respect Retry-After. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Ailoot happyhorse-1.1-r2v, happyhorse-r2v, happyhorse-r2v-latest
Use the method paths shown above.
happyhorse-r2vA video generation model driven by reference images and a text scenario. Helps preserve the appearance of characters, objects and the visual style in a new scene.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
HappyHorse-1.1-R2V creates a new video scene from reference images and a text prompt. Alibaba designs the model to preserve recognizable characters, objects and visual style while generating movement. The references establish the scene's content and appearance, and the text describes how those elements should interact.
Between one and nine images can be used. They may define a character, an object, the surroundings or an artistic treatment. The prompt can identify a reference by number and name a particular object in it, linking the visual material to the relevant part of the action. This is especially useful when elements from several images need to be combined in one composition.
Unlike the mode that uses an initial frame, references here guide the content of a new scene. A text prompt is required: it connects the appearance of objects to the action, camera movement and overall staging. The manufacturer highlights visual consistency and cinematic movement. The model generates a new video rather than editing the source images.
JPEG, JPG, PNG and WEBP files of up to 20 MB each are accepted. The shorter dimension must be at least 400 pixels; material at 720P or higher is recommended. This mode takes images and text as its inputs.
The result is saved as MP4 at 24 frames per second. Duration is specified as an integer from 3 to 15 seconds. Resolution can be selected from 480P, 720P and 1080P; audio generation is supported.
Landscape, portrait and square frames are available: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21 and 21:9. Selecting a format helps define the compositional space of the new scene in advance.
The prompt may be in any language. The limit is 5000 non-Chinese or 2500 Chinese characters, with any excess truncated. The most important reference roles, actions and movements must fit within this length. A random seed can guide similarity between variations, but does not guarantee an exact reproduction of a video.
POST /v1/videos/generationstext, imagevideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits happyhorse-r2v | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldduration | Typeinteger | RequirementOptional | Values & limits Minimum: 3 Maximum: 15 Unit: seconds | Default5 |
Fieldresolution | Typestring | RequirementOptional | Values & limits 480P, 720P, 1080P | Default720P |
Fieldratio | Typestring | RequirementOptional | Values & limits 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9 | Default16:9 |
Fieldimage_urls | Typehttps_url|data_image_url[] | RequirementRequired | Values & limits Minimum items: 1 Maximum items: 9 Maximum decoded bytes: 20,971,520 MIME types: image/jpeg, image/png, image/webp | Default— |
reference_images_to_video · Required: prompt, image_urls
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext, image |
Parameterrequired | Contractnull |
Parameteroptional_controls | Contractnull |
Lifecycle: submit_once_poll_original
GET /v1/videos/{request_id}
GET /v1/videos/generations/{request_id}
GET /v1/videos/{request_id}/content
GET /v1/videos/generations/{request_id}/content
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/videos/generationsAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_URLS_FILE:?Set a JSON file containing your actual reference-image URLs}"\nexport AILOOT_IMAGE_URLS_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "happyhorse-r2v", "prompt": "The subject walks slowly toward the camera.", "duration": 5, "resolution": "720P"}')\nfrom urllib.parse import urlsplit\nf=Path(os.environ["AILOOT_IMAGE_URLS_FILE"])\nif not f.is_file():raise SystemExit("Choose the actual reference URL JSON file")\nurls=json.loads(f.read_text())\nif not isinstance(urls,list) or not 1<=len(urls)<=9:raise SystemExit("Provide one to nine reference-image URLs")\nfor u in urls:\n z=urlsplit(u) if isinstance(u,str) else None\n if not z or z.scheme!="https" or not z.netloc or z.username or z.password:raise SystemExit("Each reference must be an actual HTTPS image URL")\np["image_urls"]=urls\np["ratio"]="16:9"\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nprint(json.dumps(r))\nPY_RESULT\nmp4
GET /v1/videos/{request_id}GET /v1/videos/generations/{request_id}GET /v1/videos/{request_id}/contentGET /v1/videos/generations/{request_id}/contentset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_OPERATION_ID:?Set the actual Ailoot operation ID returned by creation}"\nexport AILOOT_OPERATION_ID\noperation_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ["AILOOT_OPERATION_ID"],safe=""))')\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/videos/generations/$operation_id" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o status.json\npython3 - <<'PY_STATUS'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("status.json").read_text())\nprint(json.dumps(r))\nif r.get("status")=="completed":\n for x in r.get("data",[]):print(x)\nPY_STATUS\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_STATUS_FILE:?Set the actual completed status JSON file}"\nexport AILOOT_STATUS_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nfrom urllib.parse import urlsplit,urljoin\nf=Path(os.environ["AILOOT_STATUS_FILE"])\nif not f.is_file():raise SystemExit("Choose the actual completed status file")\nr=json.loads(f.read_text())\nif r.get("status")!="completed" or not isinstance(r.get("data"),list) or not r["data"]:raise SystemExit("Wait for a completed status with asset paths")\nurls=[]\nfor x in r["data"]:\n if not isinstance(x,str) or "\\n" in x or "\\r" in x:raise SystemExit("Invalid asset path")\n u=urljoin("https://api.ailoot.ai",x)\n z=urlsplit(u)\n if z.scheme!="https" or z.netloc!="api.ailoot.ai" or z.username or z.password:raise SystemExit("Use the actual Ailoot asset paths from status")\n urls.append(u)\nPath("asset-urls.txt").write_text("\\n".join(urls)+"\\n")\nPY_REQUEST\nindex=0\nwhile IFS= read -r asset_url; do\n curl --fail-with-body --silent --show-error "$asset_url" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o "video-${index}.mp4"\n index=$((index + 1))\ndone < asset-urls.txt\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_OPERATION_ID:?Set the actual Ailoot operation ID returned by creation}"\nexport AILOOT_OPERATION_ID\noperation_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ["AILOOT_OPERATION_ID"],safe=""))')\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/videos/generations/$operation_id/content" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o video.mp4\nSave every completed video or returned file; retrieve every actual returned asset URL.
Preserve every returned data item/output index. content_url is first only; fetch every actual content path/asset. GETcontentwithoutindex isnotalloutputs.
Read existing original job; never resubmit unknown send.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldobject | Typestring |
Fieldmodel | Typestring |
Fieldstatus | Typestring |
Fieldcontent_url | Typesigned URL |
Fielddata[] | Typesigned URL |
Fieldusage | Typeobject |
Fieldresult_pending_check | Typeboolean |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Response409 · video_not_ready | ConditionOriginal result content is not yet available | Next stepPoll the original returned ID and respect Retry-After. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Ailoot happyhorse-1.1-r2v, happyhorse-r2v, happyhorse-r2v-latest
Use the method paths shown above.
happyhorse-r2v-latestA video generation model driven by reference images and a text scenario. Helps preserve the appearance of characters, objects and the visual style in a new scene.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
HappyHorse-1.1-R2V creates a new video scene from reference images and a text prompt. Alibaba designs the model to preserve recognizable characters, objects and visual style while generating movement. The references establish the scene's content and appearance, and the text describes how those elements should interact.
Between one and nine images can be used. They may define a character, an object, the surroundings or an artistic treatment. The prompt can identify a reference by number and name a particular object in it, linking the visual material to the relevant part of the action. This is especially useful when elements from several images need to be combined in one composition.
Unlike the mode that uses an initial frame, references here guide the content of a new scene. A text prompt is required: it connects the appearance of objects to the action, camera movement and overall staging. The manufacturer highlights visual consistency and cinematic movement. The model generates a new video rather than editing the source images.
JPEG, JPG, PNG and WEBP files of up to 20 MB each are accepted. The shorter dimension must be at least 400 pixels; material at 720P or higher is recommended. This mode takes images and text as its inputs.
The result is saved as MP4 at 24 frames per second. Duration is specified as an integer from 3 to 15 seconds. Resolution can be selected from 480P, 720P and 1080P; audio generation is supported.
Landscape, portrait and square frames are available: 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21 and 21:9. Selecting a format helps define the compositional space of the new scene in advance.
The prompt may be in any language. The limit is 5000 non-Chinese or 2500 Chinese characters, with any excess truncated. The most important reference roles, actions and movements must fit within this length. A random seed can guide similarity between variations, but does not guarantee an exact reproduction of a video.
POST /v1/videos/generationstext, imagevideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits happyhorse-r2v-latest | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Minimum length: 1 | Default— |
Fieldduration | Typeinteger | RequirementOptional | Values & limits Minimum: 3 Maximum: 15 Unit: seconds | Default5 |
Fieldresolution | Typestring | RequirementOptional | Values & limits 480P, 720P, 1080P | Default720P |
Fieldratio | Typestring | RequirementOptional | Values & limits 16:9, 9:16, 1:1, 4:3, 3:4, 4:5, 5:4, 9:21, 21:9 | Default16:9 |
Fieldimage_urls | Typehttps_url|data_image_url[] | RequirementRequired | Values & limits Minimum items: 1 Maximum items: 9 Maximum decoded bytes: 20,971,520 MIME types: image/jpeg, image/png, image/webp | Default— |
reference_images_to_video · Required: prompt, image_urls
| Parameter | Contract |
|---|---|
Parametermaterial_types | Contracttext, image |
Parameterrequired | Contractnull |
Parameteroptional_controls | Contractnull |
Lifecycle: submit_once_poll_original
GET /v1/videos/{request_id}
GET /v1/videos/generations/{request_id}
GET /v1/videos/{request_id}/content
GET /v1/videos/generations/{request_id}/content
Method shapes and IDs are exact; supplier capability is separate from admission.
POST /v1/videos/generationsAiloot 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 →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_IMAGE_URLS_FILE:?Set a JSON file containing your actual reference-image URLs}"\nexport AILOOT_IMAGE_URLS_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "happyhorse-r2v-latest", "prompt": "The subject walks slowly toward the camera.", "duration": 5, "resolution": "720P"}')\nfrom urllib.parse import urlsplit\nf=Path(os.environ["AILOOT_IMAGE_URLS_FILE"])\nif not f.is_file():raise SystemExit("Choose the actual reference URL JSON file")\nurls=json.loads(f.read_text())\nif not isinstance(urls,list) or not 1<=len(urls)<=9:raise SystemExit("Provide one to nine reference-image URLs")\nfor u in urls:\n z=urlsplit(u) if isinstance(u,str) else None\n if not z or z.scheme!="https" or not z.netloc or z.username or z.password:raise SystemExit("Each reference must be an actual HTTPS image URL")\np["image_urls"]=urls\np["ratio"]="16:9"\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos/generations \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nprint(json.dumps(r))\nPY_RESULT\nmp4
GET /v1/videos/{request_id}GET /v1/videos/generations/{request_id}GET /v1/videos/{request_id}/contentGET /v1/videos/generations/{request_id}/contentset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_OPERATION_ID:?Set the actual Ailoot operation ID returned by creation}"\nexport AILOOT_OPERATION_ID\noperation_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ["AILOOT_OPERATION_ID"],safe=""))')\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/videos/generations/$operation_id" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o status.json\npython3 - <<'PY_STATUS'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("status.json").read_text())\nprint(json.dumps(r))\nif r.get("status")=="completed":\n for x in r.get("data",[]):print(x)\nPY_STATUS\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_STATUS_FILE:?Set the actual completed status JSON file}"\nexport AILOOT_STATUS_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nfrom urllib.parse import urlsplit,urljoin\nf=Path(os.environ["AILOOT_STATUS_FILE"])\nif not f.is_file():raise SystemExit("Choose the actual completed status file")\nr=json.loads(f.read_text())\nif r.get("status")!="completed" or not isinstance(r.get("data"),list) or not r["data"]:raise SystemExit("Wait for a completed status with asset paths")\nurls=[]\nfor x in r["data"]:\n if not isinstance(x,str) or "\\n" in x or "\\r" in x:raise SystemExit("Invalid asset path")\n u=urljoin("https://api.ailoot.ai",x)\n z=urlsplit(u)\n if z.scheme!="https" or z.netloc!="api.ailoot.ai" or z.username or z.password:raise SystemExit("Use the actual Ailoot asset paths from status")\n urls.append(u)\nPath("asset-urls.txt").write_text("\\n".join(urls)+"\\n")\nPY_REQUEST\nindex=0\nwhile IFS= read -r asset_url; do\n curl --fail-with-body --silent --show-error "$asset_url" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o "video-${index}.mp4"\n index=$((index + 1))\ndone < asset-urls.txt\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_OPERATION_ID:?Set the actual Ailoot operation ID returned by creation}"\nexport AILOOT_OPERATION_ID\noperation_id=$(python3 -c 'import os,urllib.parse;print(urllib.parse.quote(os.environ["AILOOT_OPERATION_ID"],safe=""))')\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/videos/generations/$operation_id/content" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o video.mp4\nSave every completed video or returned file; retrieve every actual returned asset URL.
Preserve every returned data item/output index. content_url is first only; fetch every actual content path/asset. GETcontentwithoutindex isnotalloutputs.
Read existing original job; never resubmit unknown send.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldobject | Typestring |
Fieldmodel | Typestring |
Fieldstatus | Typestring |
Fieldcontent_url | Typesigned URL |
Fielddata[] | Typesigned URL |
Fieldusage | Typeobject |
Fieldresult_pending_check | Typeboolean |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Response409 · video_not_ready | ConditionOriginal result content is not yet available | Next stepPoll the original returned ID and respect Retry-After. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Ailoot happyhorse-1.1-r2v, happyhorse-r2v, happyhorse-r2v-latest
Use the method paths shown above.