Dreamina Seedance 2.0——国际线。文生 / 图生 / 多模态参考,原生分辨率直出(480→480、标准版原生 4K,无放大)。真人视频需先把人像注册到素材库(account: "intl")拿到 asset:// 再引用——原始真人图会被上游内容审核直接拒(InputImageSensitiveContentDetected),asset:// 可过审。
| 字段 | 必填 | 类型 | 说明 |
|---|---|---|---|
| 模型 | API name | 分辨率 | 计费(每秒) |
| Dreamina Seedance 2.0 | dreamina-seedance-2-0 | 480p / 720p / 1080p / 原生 4K | $0.10 / $0.22 / $0.55 / $2.57 |
| Dreamina Seedance 2.0 Fast | dreamina-seedance-2-0-fast | 480p / 720p | $0.0644 / $0.1372 |
| Dreamina Seedance 2.0 Mini | dreamina-seedance-2-0-mini | 480p / 720p | $0.0225 / $0.048 |
按秒计费(时长 4-15 秒),仅成功扣费、失败退款。分辨率原生直出,不做放大。
2026 年 8 月 8 日降价:Mini 降约 56%、Fast 降约 24%,标准档价格不变。带参考视频的任务按另一个口径计费——单价更低,但按「源片秒数 + 输出秒数」计,所以编辑或续写一段与成片等长的素材,并不比直接生成便宜。Mini $0.0138 / $0.030,Fast $0.0378 / $0.0812(480p / 720p)。
/api/v1/video/generations# Text-to-video (model: dreamina-seedance-2-0 / -fast / -mini)
curl -X POST https://api.apimodels.app/v1/video/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "dreamina-seedance-2-0-fast",
"prompt": "a hummingbird hovering near a bright flower, slow motion",
"resolution": "720p",
"aspect_ratio": "16:9",
"duration": 5
}'
# Real-person: register the face in the asset library first (account "intl", see below),
# then reference it — a RAW real face URL is rejected at create-time
# (InputImageSensitiveContentDetected.PrivacyInformation), asset:// passes:
# "reference_image_urls": ["asset://asset-2026...-xxxx"]
#
# Image-to-video of a specific real person: pass the asset:// AS the first frame.
# (first_frame_url and reference_image_urls are mutually exclusive — when a first
# frame is present, reference_image_urls is ignored, so put the person there):
# "first_frame_url": "asset://asset-2026...-xxxx"| 字段 | 必填 | 类型 | 说明 |
|---|---|---|---|
| 字段 | 类型 | 说明 | |
| model | string | dreamina-seedance-2-0 / -fast / -mini | |
| prompt | string | 提示词(文生视频必填;有视觉输入时可选) | |
| resolution | string | 480p / 720p / 1080p / 4k(fast、mini 仅 480p/720p) | |
| aspect_ratio | string | adaptive / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / 21:9 | |
| duration | number | 4-15 秒 | |
| generate_audio | boolean | 原生同步音频,默认 true | |
| content_filter | boolean | 内容审核,默认 true(标准审核)。传 false 可放宽内容限制,该次请求按 +10% 计费;违法违禁内容无论如何都拦。不传 = 标准审核、原价。 | |
| first_frame_url / last_frame_url | string | 图生视频首/尾帧(https:// 或 asset://) | |
| reference_image_urls / _video_urls / _audio_urls | string[] | 多模态参考,支持 https:// 或 asset://(真人用 asset://) | |
| web_search | boolean | 联网搜索工具 |
写实真人脸直接当输入图会被上游内容审核拒(报 "may contain real person")。要生成真人视频,先把人像上传到素材库拿到 asset:// 引用,再传入。分组创建时必须带 account: "intl"(与国际版生成同账号/项目 billing19),素材才解析得到;上传成功每条计 $0.01。
# 1) Create a group ON THE INTL account (account: "intl")
curl -X POST https://api.apimodels.app/v1/assets/groups \
-H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" \
-d '{"name": "my-people", "account": "intl"}'
# → { "data": { "id": 1, "account": "intl", ... } }
# 2) Register a face from a public URL. The call WAITS until the asset is confirmed
# usable (~3s), so the returned id is ready to use right away. Charged $0.01 ONLY
# on success — if the image can't be fetched or fails moderation you get HTTP 422
# and are NOT charged.
curl -X POST https://api.apimodels.app/v1/assets \
-H "Authorization: Bearer YOUR_API_KEY" -H "Content-Type: application/json" \
-d '{"url": "https://example.com/face.jpg", "asset_type": "Image", "group_id": 1}'
# → { "data": { "id": "asset-2026...-xxxx", "asset_url": "asset://asset-2026...-xxxx", "status": "Active" } }
# (on failure: HTTP 422, not charged)
# 3) Use asset_url in generation — either reference_image_urls (multi-image) or, to
# animate that exact person, first_frame_url. No polling needed once Active.| 字段 | 必填 | 类型 | 说明 |
|---|---|---|---|
| 端点 | 说明 | ||
| POST /v1/assets/groups | 建分组,传 account:"intl" → 国际版账号(billing19) | ||
| POST /v1/assets | 从 URL 注册人像 → asset://($0.01),继承分组账号 | ||
| POST /v1/assets/get | 查询单个素材(轮询到 Active) | ||
| POST /v1/assets/list | 分页列出素材 | ||
| POST /v1/assets/delete | 删除素材 |
Playground 有两个上传:「任务肖像」和「参考图」。真人一律走「任务肖像」—— 它会把人脸自动注册成 asset:// 并过审,这是真人的唯一正确入口。四步:
| 字段 | 必填 | 类型 | 说明 |
|---|---|---|---|
| 你想要 | 怎么传 | ||
| 只要一段真人视频 | 只传「任务肖像」(一张人脸),文生视频模式 | ||
| 真人 + 额外的场景 / 风格参考 | 肖像 + 参考图(非真人),用「多图参考」/「多模态参考」模式 | ||
| 让某张真人照片作为首帧动起来 | Playground 暂不支持;走 API,把该人像 asset:// 放进 first_frame_url(见上方代码) |
试一试:Playground
先把人像注册到素材库(account "intl")拿到 asset://,再作为 reference_image_urls 传;若要让这个人动起来,就把 asset:// 放进 first_frame_url。原始真人图会被审核拒,asset:// 可过审。