jimeng-cli-image2video

Dreamina 即梦 CLI image-to-video

First choose the command based on input intent, then run the corresponding dreamina <command> -h：

When to use and boundary

For CLI video tasks that have at least one reference image or one reference video. Should not be used for text-only video, image generation, or prompt-only polishing; use the corresponding jimeng-cli-* or jimeng-prompt-* skill for those scenarios.

Scenario	Command	Key input
Single-image animation	image2video	--image, required --prompt
First-and-last-frame transition	frames2video	--first、--last
2–20 storyboard frames	multiframe2video	--images
Image/video/audio all-reference	multimodal2video	At least one image or one video

v1.4.14 hard constraints

• All four modes must explicitly pass --video_resolution。
• Resolution tokens use lowercase 720p、1080p、4k。
• multiframe2video fixed model, only accepts 720p/1080p.
• The other three modes only have seedance2.0_vip available in 1080p/4k, other models only 720p.
• image2video Supports seedance1.0fast、seedance1.5pro and the Seedance 2.0 family.
• frames2video Supports seedance1.5pro and the Seedance 2.0 family.
• multimodal2video Only supports the Seedance 2.0 family, audio cannot be the only input.

For the full matrix see dreamina-cli skill's v1.4.14 contract(if not installed:npx skills add full-aigc-skills/jimeng-skills --skill dreamina-cli)。

Minimal correct example

dreamina image2video --image=./photo.png --prompt="镜头缓慢推近" --video_resolution=720p --poll=0
dreamina frames2video --first=./start.png --last=./end.png --prompt="季节自然变化" --video_resolution=720p --poll=0
dreamina multiframe2video --images=./a.png,./b.png --prompt="人物转身走向远处" --video_resolution=720p --poll=0
dreamina multimodal2video --image=./subject.png --audio=./music.mp3 --prompt="按音乐节奏运镜" --video_resolution=720p --poll=0

For multi-frame stories with more than 3 frames, every N images provides N−1 transitions; single segment duration 1–8 seconds:

dreamina multiframe2video \
  --images=./a.png,./b.png,./c.png \
  --transition-prompt="从 A 走向 B" \
  --transition-prompt="从 B 走向 C" \
  --transition-duration=3 \
  --transition-duration=3 \
  --video_resolution=1080p \
  --poll=0

Asynchronous closed loop

Step 1: Routing and validation

Choose one of the four commands based on input intent, verify the file is readable, then use the corresponding help to validate model, duration, and resolution.

Step 2: Submission

Check credits, explain the consumption impact, submit asynchronously, and save submit_id。

Step 3: Final-state closed loop

For querying keep calling query_result, until success or fail. On failure report fail_reason. When encountering AigcComplianceConfirmationRequired , prompt the user to complete authorization on the Web side first.

Gotchas

1. Mode misrouting: single image, first-and-last frame, storyboard, and all-reference have different parameter names.
2. Missing resolution: all four commands must pass video_resolution。
3. Multi-frame overreach: multiframe does not accept model_version, and cannot use 4k.
4. Transition count: N images require N−1 transitions.
5. Audio submitted alone: multimodal requires at least one image or one video.

References

• dreamina-cli skill's v1.4.14 parameter contract(if not installed:npx skills add full-aigc-skills/jimeng-skills --skill dreamina-cli)
• Mode selection
• Parameter reference
• VIP guide
• Workflow mode
• Examples