القائمة
Generate videos with BytePlus Seedance. Use for Seedance text-to-video, image-to-video, camera control, and draft video workflows.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | polym-eval-generate-seedance |
| description | Generate videos with BytePlus Seedance. Use for Seedance text-to-video, image-to-video, camera control, and draft video workflows. |
Generate videos using BytePlus Seedance via the Ark SDK.
API Reference: https://docs.byteplus.com/en/docs/ModelArk/1366799
Before generating, verify in .env:
BYTEPLUS_API_KEY (Required)BYTEPLUS_BASE_URL (default: https://ark.ap-southeast.bytepluses.com/api/v3)SEEDANCE_MODEL (optional, default from env)TOS_BUCKET, TOS_ACCESS_KEY, TOS_SECRET_KEY# Text-to-Video
python skills/polym-eval-generate-seedance/scripts/generate.py \
--prompt "A cat playing with a ball of yarn" \
--model seedance-1-5-pro-251215
# Image-to-Video (first frame)
python skills/polym-eval-generate-seedance/scripts/generate.py \
--prompt "The scene comes alive with gentle motion" \
--first-frame photo.jpg \
--model seedance-1-5-pro-251215
| Parameter | CLI Flag | Type | Description | Default |
|---|---|---|---|---|
prompt | --prompt, -p | string | Text prompt | Required |
model | --model, -m | string | Model ID | env SEEDANCE_MODEL |
first_frame | --first-frame | string | First frame image path/URL (I2V) | None |
last_frame | --last-frame | string | Last frame image path/URL | None |
seconds | --seconds, -d | int | Duration (2-12s, 1.5-pro: 4-12s) | 8 |
size | --size, -s | string | Resolution: 480p, 720p, 1080p | 720p |
aspect_ratio | --aspect-ratio | string | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive | auto-detect |
watermark | --watermark | flag | Add watermark | False |
camerafixed | --camerafixed | flag | Fix camera position | False |
draft | --draft | flag | Draft mode (480p only, faster) | False |
seed | --seed | int | Random seed | None |
output | --output, -o | string | Output path | generated/{id}.mp4 |
| Model | Resolution | Duration | Notes |
|---|---|---|---|
seedance-1-5-pro-251215 | 480p/720p/1080p | 4-12s | Latest, native audio |
seedance-1-0-pro-250528 | 480p/720p/1080p | 2-12s | Strong visual consistency |
seedance-1-0-pro-fast-251015 | 480p/720p/1080p | 2-12s | Low latency |
seedance-1-0-lite-t2v-250428 | 480p/720p/1080p | 2-12s | T2V only |
seedance-1-0-lite-i2v-250428 | 480p/720p | 2-12s | I2V only |
--first-frame photo.jpg--last-frame photo.jpg--first-frame and --last-frameAspect ratio is auto-detected from reference images. Params are auto-validated/adjusted per model capabilities.
byteplussdkarkruntime
Pillow
requests
python-dotenv
tqdm
tos # for reference image upload
Set it in .env.
Use 720p for lite I2V models.
This is by design — draft mode only supports 480p for faster generation.
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 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".
Generate Slack daily digests, highlight customer risks and action items, and publish summaries to Lark or local outputs.