원클릭으로
polym-eval-generate-sora
Generate videos with Sora via OpenAI or ByteDance AIDP. Use for Sora 2/Pro text-to-video and image-to-video workflows.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Generate videos with Sora via OpenAI or ByteDance AIDP. Use for Sora 2/Pro text-to-video and image-to-video workflows.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | polym-eval-generate-sora |
| description | Generate videos with Sora via OpenAI or ByteDance AIDP. Use for Sora 2/Pro text-to-video and image-to-video workflows. |
Generate videos using Sora models.
Supports two backends:
openai (default): OpenAI public API — sora-2, sora-2-proaidp: ByteDance AIDP model hub — azure-sora2 (recommended), azure-sora (legacy T2V only)Both T2V (text-to-video) and I2V (image-to-video, first-frame reference) are supported. Auto aspect ratio detection from the reference image.
# Required
export OPENAI_API_KEY="sk-..."
If OPENAI_API_KEY is not set, the script will prompt you to enter it and save it to .env.
# Required
export AIDP_AK="your-aidp-ak"
Note for
azure-sora2: The "账号粘性功能开关" must be enabled in your AIDP platform account forazure-sora2to work correctly. Contact the AIDP platform team if unsure.
cd skills/polym-eval-generate-sora
pip install -r requirements.txt
# T2V
python scripts/generate.py \
--prompt "A serene lake reflecting autumn trees at sunset" \
--seconds 8
# I2V (first-frame reference)
python scripts/generate.py \
--prompt "The scene gently animates" \
--first-frame /path/to/photo.jpg \
--seconds 8
# T2V
python scripts/generate.py \
--backend aidp \
--prompt "A serene lake reflecting autumn trees at sunset" \
--seconds 5
# I2V
python scripts/generate.py \
--backend aidp \
--prompt "The scene gently animates" \
--first-frame /path/to/photo.jpg \
--seconds 5
# Use legacy azure-sora (T2V only)
python scripts/generate.py \
--backend aidp --model azure-sora \
--prompt "A serene lake" \
--seconds 5
| Flag | Default | Description |
|---|---|---|
--prompt / -p | required | Text prompt |
--backend | openai | openai or aidp |
--model / -m | sora-2 (openai) / azure-sora2 (aidp) | Model override |
--first-frame | None | Reference image path or URL (I2V) |
--seconds / -d | 8 | Duration in seconds |
--size / -s | auto-detected | Explicit size e.g. 1280x720 |
--resolution | 720p | Resolution tier: 720p or 1080p |
--output / -o | generated/<id>.mp4 | Output path |
| Backend | Model | Mode | Notes |
|---|---|---|---|
| openai | sora-2 | T2V, I2V | Default OpenAI model |
| openai | sora-2-pro | T2V, I2V | Higher quality |
| aidp | azure-sora2 | T2V, I2V | Recommended AIDP model |
| aidp | azure-sora | T2V only | Legacy; no I2V support |
| Variable | Required | Description |
|---|---|---|
OPENAI_API_KEY | Yes | OpenAI API key |
SORA_MODEL | No | Default model (default: sora-2) |
TOS_BUCKET | No | TOS bucket for network URL |
TOS_ACCESS_KEY | No | TOS access key |
TOS_SECRET_KEY | No | TOS secret key |
| Variable | Required | Description |
|---|---|---|
AIDP_AK | Yes | AIDP API Key (ak) |
AIDP_HOST | No | AIDP host (default: aidp.bytedance.net) |
SORA_AIDP_MODEL | No | Default AIDP model (default: azure-sora2) |
{
"gen_success": true,
"gen_video_path": "generated/abc12345.mp4",
"gen_url": "https://...",
"gen_elapsed": 120,
"gen_failed_reason": null
}
POST /sora/v1/videos?ak={ak} (multipart form-data)GET /sora/v1/videos/{id}?ak={ak}&product=azure_sora2file_tos_url field in response, downloaded from https://tosv.byted.org/obj/{file_tos_url}input_reference field)POST /sora/v2/generate?ak={ak} (form-data: height, width, n_seconds)POST /sora/v2/fetch?ak={ak} (body: {"model":"azure-sora","taskid":"..."})requests
Pillow
python-dotenv
Optional (for TOS upload / network URL with OpenAI backend):
tos
OPENAI_API_KEY not set: Script will prompt for input and save to .env.AIDP_AK not set: Script will prompt for input and save to .env.azure-sora2 for I2V.tosv.byted.org (ByteDance internal network required).max_wait in aidp_wait_for_completion / wait_for_completion.Research BytePlus products, APIs, SDKs, setup, quotas, regions, pricing, and troubleshooting using the bundled official documentation index, then verify claims on live docs. Use for requests for BytePlus documentation or official links.
Batch-generate Seedance 2.0 Mini videos via the BytePlus console BFF (Mini has no public API). Covers T2V, image/video reference (I2V/R2V), first/last frame, and human portraits. Triggers: "seedance mini", "dreamina mini", "用 mini 出视频".
Generate textured 3D models (GLB + PBR) from an image and/or text prompt via Volcengine Ark Seed3D (doubao-seed3d). Submits the async task, polls to completion, and downloads the .glb. Domestic Volcengine Ark only, not BytePlus overseas.
Generate videos with BytePlus Seedance. Use for Seedance text-to-video, image-to-video, camera control, and draft video workflows.
Generate images with BytePlus Seedream 4.x/4.5. Use for Seedream text-to-image, AI art, product images, and batch image generation.
Creates polished explainer videos from docs, URLs, PDFs, screenshots, or text. Use for product demos, announcement reels, repo videos, and requests like "make an explainer video" or "turn this repo into a video".