Vibe FilmingAI Video from Idea to Screen

1A. Clip A · own face · English

Requires one ready portrait in your authorized group.

@Image 1 defines my face and hairstyle. One adult in a plain navy jacket stands beside a Hong Kong harbour railing at golden hour. Preserve the referenced identity. Begin waist-up, then slowly push in as I turn from the harbour toward the lens. I settle into a relaxed smile, hands still on the railing. Hold the final pose for the last two seconds, mouth closed. Keep one person, the same clothes and warm light. Soft harbour ambience; no speech, music, text or logos.

1A. Clip A · Traditional Chinese support

@圖片1 定義我的面孔與髮型。一名成人穿著素色深藍外套，站在黃昏香港海旁欄杆邊，保留參考照片的人物身份。起初腰部以上入鏡，鏡頭緩緩推近，我由望向海港轉為望向鏡頭，自然微笑，雙手靜放在欄杆上。最後兩秒保持姿勢，嘴巴合上。全片保持同一人、服裝和暖光。只有輕柔海港環境聲，不加說話、音樂、文字或標誌。

1B. Clip B · A final frame · English

Requires the PNG extracted from downloaded Clip A.

Start exactly from the supplied first frame. Preserve the same person's face, hairstyle, navy jacket, hand positions, railing, harbour and golden-hour light. Hold that pose briefly, then make one slow, small camera arc to reveal more of the harbour. The person keeps a relaxed smile, mouth closed, and remains recognizable. Finish with the person and harbour both visible. Keep one person. Soft harbour ambience; no speech, music, text or logos. Do not restart the previous turn.

1B. Clip B · Traditional Chinese support

由提供的首幀開始，保留同一人的面孔、髮型、深藍外套、手部位置、欄杆、海港與黃昏暖光。先短暫保持該姿勢，再讓鏡頭緩慢地小幅環繞，展露更多海港。人物保持自然微笑、嘴巴合上，身份清晰可辨。最後同時看見人物與海港。全片只有一人。只有輕柔海港環境聲，不加說話、音樂、文字或標誌。不要重新做上一段的轉身。

Optional · original fictional AI face

Text-only A route; continue B from its extracted final frame.

Create an original fictional adult with short dark hair; do not imitate a named real person. One adult in a plain navy jacket stands beside a Hong Kong harbour railing at golden hour. Keep this fictional face consistent. Begin waist-up, then slowly push in as I turn from the harbour toward the lens. I settle into a relaxed smile, hands still on the railing. Hold the final pose for the last two seconds, mouth closed. Keep one person, the same clothes and warm light. Soft harbour ambience; no speech, music, text or logos.

1. Install

curl -fsSL https://holycrab.ai/cli/install.sh | sh
holycrab --version
holycrab --help

2. Configure locally

holycrab setup
holycrab auth status
holycrab models list
holycrab models show dreamina-seedance-2-5-260628

3. Fetch workshop prompts

mkdir -p ai-video-workshop
cd ai-video-workshop
curl -fL 'https://brucehuang.ai/talks/ai-ultra-video-workshop-2026-09/prompts/clip-a-en.txt' -o prompt-a.txt
curl -fL 'https://brucehuang.ai/talks/ai-ultra-video-workshop-2026-09/prompts/clip-b-en.txt' -o prompt-b.txt

4. Private real-person authorization

holycrab real-human groups list
# Only when the participant requests a new authorization:
holycrab real-human start --name "My workshop portrait"
# Keep the returned link/QR private; complete verification yourself.
holycrab real-human wait AUTHORIZATION_ID --timeout 60

5. Complete Coding Agent instruction

Use the installed official HolyCrab skill and current CLI help. Help me create two connected 10-second Seedance 2.5 clips at 480p, within 500 credits total. A starts at 16:9; B uses frames mode and adaptive ratio. First ask whether I choose my own face or an original fictional AI face. Fetch clip-a-en.txt and clip-b-en.txt from https://brucehuang.ai/talks/ai-ultra-video-workshop-2026-09/prompts/; use ai-face.txt for fictional Clip A. Save all working files locally.
For my own face, check my existing authorized group. Only start a new authorization if I request it. Show the temporary verification link/QR privately to me; I complete verification myself. Never save that link/QR in files, logs or the public kit. After SUCCEEDED, upload only my selected portrait into my own authorized group and wait for ready:true. Never bypass failed verification with ordinary upload. Use my web account's matching CLI access; do not assume another key can use my group.
Prepare Clip A with the returned ready public portrait asset ID in imageAssetIds. For the fictional route, prepare A as text-only. Estimate the actual payload and show credits, settings and remaining balance privately. Planning quote: A 139 + B 139 = 278 credits; one optional 10s retry brings the total to 417. Quotes can change with actual assets. Keep a cumulative ledger, and stop before exceeding 500. Wait for my explicit approval before each paid submission; do not treat this instruction as approval. Submit once, record the task ID immediately, and recover that existing task after interruption.
Download completed A as clip-a.mp4. Extract and inspect its last frame as last-frame.png. For my real face, upload this derived frame to my same authorized group and wait for ready:true; stop if the service does not accept the group/frame route, without trying an ordinary-upload bypass. For the original fictional face, use ordinary asset upload. Prepare B with firstFrameAssetId set to this new ready asset ID, videoTaskType frames, ratio adaptive, 10 seconds, 480p. Do not combine frames with imageAssetIds or other reference arrays. Re-estimate B and ask for approval, then submit exactly once and download clip-b.mp4. Place A then B in an editor, inspect the seam and audio, and export the 20-second film. Keep source portrait/frame IDs, prompts, settings, quotes, task IDs and review notes. Never print credentials or clone my real voice. Ask separately before sharing my output.

5. Traditional Chinese Agent reference

使用 HolyCrab 官方 skill 和目前 CLI help，在500 credits總額內準備兩段10秒Seedance2.5、480p影片。A用16:9；B用frames模式、adaptive比例。先確認我選本人或原創AI臉。本人需親自完成私下驗證，SUCCEEDED後才把指定照片上傳到本人授權群組，等待ready:true；不能普通上傳繞過授權失敗。AI臉的A用純文字。逐條估價並取得明確確認才付費提交，立即保存task ID，中斷找回同一任務。預算A139+B139=278，一次10秒重試後417，實際素材需重新估價，不超過500。下載A，抽取並檢查末幀；真人末幀必須回到本人同一授權群組，等ready。B只以此素材作firstFrameAssetId，不混用imageAssetIds或其他參考。再估價、確認、提交、下載B。剪輯器中依次放A和B，檢查接點與聲音，輸出20秒影片。保存素材ID、Prompt、參數、估價、task ID和檢查紀錄。私密驗證連結／QR及Key不進入文件、日誌或群聊；不可代本人驗證。

6. Extract the final frame locally

# Optional local FFmpeg route; the browser tool needs no installation.
# Decode the final 0.2 seconds and keep the last decoded frame.
ffmpeg -sseof -0.2 -i clip-a.mp4 -update 1 last-frame.png
# Inspect the PNG before uploading it. Use a new filename if it already exists.

7. Authorization and asset readiness

# After personal authorization SUCCEEDED, use your returned public group ID.
holycrab assets upload ./my-portrait.jpg --real-human-group GROUP_ID
holycrab assets wait PORTRAIT_ASSET_ID --timeout 60
# After A completes, reuse the SAME authorized group for its derived frame.
holycrab assets upload ./last-frame.png --real-human-group GROUP_ID
holycrab assets wait FRAME_ASSET_ID --timeout 60
# B uses FRAME_ASSET_ID only as firstFrameAssetId. No imageAssetIds.

8. Estimate before submission

Save real-face A or AI-face A as request-a.json. Save continuation B as request-b.json. Replace placeholders only with your own returned ready asset IDs. Clip B uses adaptive ratio inherited from the frame.

# Save the A template as request-a.json and B template as request-b.json.
# Replace each marked asset ID with its returned ready ID.
holycrab generate estimate --kind video --json @request-a.json
# Quote B separately after its actual frame asset is ready.
holycrab generate estimate --kind video --json @request-b.json

9. Recover and download

holycrab tasks list --page 1 --page-size 10
holycrab tasks get TASK_ID
holycrab tasks wait TASK_ID --timeout 120
holycrab download TASK_ID --output ./clip-a.mp4