
Shotkiln: AI Short Video Lab
Turn an idea, script, product photos or a start frame into one AI-generated 4-7 second 720p video with audio per message, made with ByteDance Seedance 2.0 Mini. You approve a shot plan first. Remix mode builds a new clip from your video's first frame with one change applied. Clips can be joined into a longer sequence.
#الفيديو
التقييم
مطلوب المزيد من التقييمات
المبيعات
0
كيفية الاستخدام
التشغيل على Capafy
متاح أيضًا في التطبيقات الخارجية
يوفّره الناشر
google/gemini-3.8-flash
Shotkiln: AI Short Video Lab
Shotkiln turns an idea, script, product photos or a start frame into one new AI-generated video clip of 4-7 seconds at 720p with AI audio per message.
What it does
- Writes a short shot plan (subject, action, setting, camera, audio, length, aspect ratio) for you to approve before anything is generated.
- Generates one clip per message from text, optionally with up to 4 reference images, or from a first frame (and optional last frame) that you upload.
- Remix: takes the first frame of a video you upload and generates a new clip from it with one change you describe. It does not edit your original footage; the motion, timing and audio of the original are not kept. Video links aren't supported; upload the file.
- Joins clips you already made into one longer MP4, locally and at no cost.
- Aspect ratios: 9:16, 16:9 or 1:1.
How to use it
Example prompts:
- "A 6-second vertical clip: a ceramic coffee mug on a sunny kitchen counter, steam rising, slow push-in, soft café sounds."
- "Use this product photo as a reference: the sneaker rotating on a white turntable, 7 seconds, 1:1."
- "Start from this image and animate the curtains blowing in the wind."
- "Remix my clip: same scene but at night with neon lights." (upload the video)
- "Join my last three clips."
What you get
- An MP4 clip (720p, with AI-generated audio) from the printed output path, plus the shot plan used.
- Clips are AI-generated and can differ from the plan. No views or reach are promised.
- No real private people without consent, no copyrighted characters, celebrities or third-party logos.
Limits per message (enforced in code)
- 1 generated clip per message. A second generation, or a retry of a failed one, in the same message is refused.
- Clip length 4-7 seconds. Longer requests are refused; make several clips and join them.
- Resolution fixed at 720p.
- Prompt up to 2,000 characters. Up to 4 reference images, each up to 10 MB.
- At most 6 clips per rolling 24 hours (best effort). Joining clips is free and not limited per message.
Model
- Video:
bytedance/seedance-2.0-minithrough OpenRouter's video API, 720p with audio. - The assistant runs on
google/gemini-3.8-flashthrough OpenRouter with reasoning effort set to low. It makes at most 3 model calls per message (plus up to 2 short summary calls if that limit is reached).
Plans and prices
One request = one message you send.
| Plan | Price | Requests (messages) |
|---|---|---|
| Day | $8.49 | 6 |
| Week | $14.39 | 9 |
| Month | $26.99 | 18 |
No free trial on any plan.
Data handling
- Your messages and uploaded files are processed inside this agent's Capafy run sandbox.
- Your final prompt and any reference, first-frame or last-frame images (for remix, the extracted first frame) are sent to OpenRouter, which forwards them to ByteDance's Seedance 2.0 Mini model to generate the clip. Your chat messages are processed by
google/gemini-3.8-flashthrough OpenRouter. - Results are written to the sandbox's
output/folder and returned to you in the chat. - A small usage file in the sandbox home folder stores only timestamps and counts (no prompts or file contents). It enforces the per-message and per-24-hour limits.
- The package does not send your content to any other service, and it has no analytics or tracking.
- API keys are the publisher's hosted keys. You don't need to provide any key, and the package never prints or stores keys.
- Don't upload anything you are not allowed to share with these model providers.
Support
Questions or problems: [email protected]

