Nodes/comfyui-evolink/EvoLink Seedance 2.0 Mini Image-to-Video (Official)
ComfyUI Node

EvoLink Seedance 2.0 Mini Image-to-Video (Official)

The cheapest way to animate a frame

By deeplearning-goethe·Created 24 days ago·Updated a day ago· 0
EvoLink Seedance 2.0 Mini Image-to-Video (Official)
  • first_frame
  • last_frame
  • video
  • task_id
  • status_info
  • result_urls
  • response_json
prompt
duration5
quality720p
aspect_ratioadaptive
generate_audiotrue
api_key
timeout_seconds1800

Image-to-video is the most controllable kind of cloud video, and Mini is the cheapest flavor of it in the EvoLink pack. EvoLink Seedance 2.0 Mini Image-to-Video (Official) takes a required first_frame, an optional last_frame, and a prompt, and gives you a 4-to-15-second clip capped at 720p. If you want to learn first/last-frame animation without spending flagship money on every attempt, this is the node to make your mistakes on.

What it is

  • first_frame (required) - the starting image from any image output. Local files upload through EvoLink's channel and are auto-deleted after 72 hours. The clip's aspect ratio follows this frame.
  • last_frame (optional) - the ending image; connect it and the video is forced to travel from frame A to frame B. Mismatched ratios auto-align to the first frame.
  • prompt (required) - the motion description, Chinese welcome.
  • duration - 4–15 seconds, default 5, billed by duration.
  • quality - 480p or 720p. Mini has no 1080p/4K - that's the point of the tier.
  • generate_audio - on by default, no extra charge.

Outputs: video (into Save Video - nothing visible otherwise), task_id, status_info, result_urls (24-hour expiry), response_json. Default timeout 30 minutes; renders are remote, so "Mini" means cheap, not instant.

Install and key

Standard EvoLink install - same for every node here. ComfyUI Manager → search EvoLink → install → full restart (close the console, don't just refresh the browser). Manual:

cd ComfyUI/custom_nodes
git clone https://github.com/deeplearning-goethe/comfyui-evolink

Dependency is just requests; no models, no GPU. Key from evolink.ai/dashboard/keys (sk-), pasted once into api_key - saved locally, blank after, never in a shared workflow.

Why you'd specifically pick Mini

Two reasons. First: it's the cheap way to iterate on "will this frame move well" before you commit the good frames to a pricier render. Second: the loop trick - feed your first frame as the last frame too, and Mini becomes the cheapest loop generator in the pack, because the model has to return to where it started. It won't be your most polished loop ever at 720p, but it'll be your cheapest, which is often the point.

The trade is the same one the whole Mini line makes: it's visibly a budget render, so finals belong on the full Seedance 2.0 I2V. And the standing cloud math applies - per-call billing, prompts and frames leave the machine, failed or moderation-blocked tasks don't charge. Cheap tier, real meter, same deal.

CategoryEvoLink

Inputs (9)

NameTypeDefaultDescription
promptSTRING镜头/画面描述,支持中文(建议 500 字内)。接 first_frame 出图生视频,可再接 last_frame 做首尾帧。
first_frameIMAGE首帧图(必接)
durationoptINT54–15视频时长(秒),4~15 任意整数,按时长计费
qualityoptCOMBO720p分辨率;480p 更便宜
aspect_ratiooptCOMBOadaptive画幅;adaptive 由模型自动选择
generate_audiooptBOOLEANtrue生成同步音频(不额外收费)
last_frameoptIMAGE尾帧图(可选,接上即首尾帧模式;比例不同时自动对齐首帧)
api_keyoptSTRINGEvoLink API Key(sk- 开头)。首次填写后自动保存到本机配置,之后可留空。分享工作流前请清空此框。获取:evolink.ai/dashboard/keys
timeout_secondsoptINT180060–3600最长等待时间;生成失败或审核拦截的任务不扣费

Outputs (5)

NameTypeDescription
videoVIDEO生成结果(已下载落地,可直连保存节点)
task_idSTRINGEvoLink 任务 ID,可到 evolink.ai/zh/dashboard/logs 查询
status_infoSTRING人读状态摘要(模型/用时/消耗 credits)
result_urlsSTRING结果原始链接,每行一个(24 小时过期)
response_jsonSTRING平台 GET /v1/tasks/{id} 的完整 JSON 响应(status/usage/results 等),供下游节点解析