[verdict][curated prompt][source: ghostfeed.ai]
Can I vibecode Ghostfeed?
// buildable in a weekend, but real gaps stay open
No model here was trained by Ghostfeed · every step is somebody else's hosted inference, spread across four vendors. A Gemini image-edit call swaps your avatar into frame 0 of an existing clip, an approval gate makes you accept that frame before anything expensive runs, and then the video step splits: the default clone family sends the approved frame plus the original clip to Kling motion-control, so the render inherits the source video's motion, while the prompt family animates the still alone on PixVerse, Seedance, Grok or Kling. Rebuild the loop for yourself with a fal.ai key, a Gemini key and ffmpeg over a long weekend and it works. What does not fall out of that weekend is the rest of it · a template library scraped and scene-cut into 9:16 clips, a director that writes slideshow copy and casts every background itself, a timeline editor with its own render workers, 44 agent-API tools, and a TikTok app that took platform review to get. Personal version, yes. The thing you would actually run daily, no.
confidence: high
what it is: Drops your AI avatar into a viral creator's clip and clones its motion, builds TikTok photo slideshows, and hands them to TikTok
Buildability index · an editorial game
- Price 49 $/month weight: plus 3
- Time multi-day weight: plus 1
- Category ai video no weight
- Moat execution quality · integrations weight: minus 2
- Confidence high weight: plus 1
- What you lose 5 items weight: minus 2
- Site ghostfeed.ai (si apre in una nuova scheda) no weight
They cancel out. This is where it comes down to how much the subscription annoys you.
Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.
// free tier: The free plan renders no video at all: one slideshow project with three variants, one workspace, library and posting access, and the agent API, which is ungated on every plan including this one.
What you build
Swap an avatar photo into frame 0 of a reaction clip with a hosted image-edit model, approve that frame, then send it plus the source clip to a hosted motion-control model so the render copies the original's motion, and burn the hook text over the result.
what you need
- fal.ai key for Kling motion-control and image-to-video
- Gemini or GPT-image key for the first-frame swap
- ffmpeg
- reaction clips you have the right to reuse
- an always-on box for the polling loop
Submitted by the founder · written against the honest DIY, and the DIY here is real, so it is a kinda.
The prompt
A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.
Build me a personal UGC reaction video factory to replace Ghostfeed. Requirements:
- Node + Express + better-sqlite3, a localhost dashboard with three panes: my
avatar photos, a folder of reaction clips I own, and a render queue.
- First frame: pull frame 0 from a chosen clip with ffmpeg, send it plus my
avatar photo to Gemini's image-edit API (key in .env) and tell it to replace
the whole person while holding the pose, framing, and lighting. Keep that
instruction in prompts/first-frame.txt so I can tune it without code changes.
- Nothing animates until I approve the frame, so give me approve, regenerate,
and discard buttons · the frame costs cents on my invoice, the video dollars.
- Motion: on approve, POST the frame AND the original clip to fal.ai's Kling
motion-control queue so the render copies the source video's motion, poll to
done, write the mp4 to media/, store the real cost on the row.
- Second mode: animate the frame alone from a written motion prompt via
fal.ai's PixVerse image-to-video, for when I have no clip worth copying.
- Burn the hook line over the top third with ffmpeg drawtext, 1080x1920 out,
clear of the TikTok UI safe area.
- A node-cron tick polls pending jobs every 90s, retries 3 times with backoff,
and marks the row before submitting so a retry never double-bills me.
- No accounts, no telemetry, everything on my disk except the model calls.
- Out of scope: posting to TikTok (that OAuth review takes weeks · export the
mp4 and upload by hand), slideshows, and teams. Only ingest clips I have the
right to use.
- README: getting the two keys, what one 5-second motion-control render costs,
and where media lands on disk.Curated prompt: written and reviewed by hand for this app. In English on purpose — it is the language coding agents work best in.
What you lose
- a template library scraped from TikTok and Instagram and scene-cut into ready 9:16 clips, instead of clips you source and trim yourself
- avatar consistency across renders · one stored reference photo re-fed into every call, plus the draft-and-approve flow that keeps a face you picked
- a director loop that writes the slideshow copy, searches for backgrounds, looks at the candidates and casts them, then rotates the deck into variants, plus a timeline editor with its own render workers
- 44 agent-API tools · the same workspace drivable from Claude, which is the part with no weekend equivalent
- a TikTok app that already cleared review, and a reaper that refunds most stalled renders instead of quietly eating them
Why people still pay
The generation stack spans Google, fal.ai, Replicate and BytePlus, and any one of them can change price, quality or content filters in a week · the subscription outsources that churn and turns per-second render invoices into one number. Stalled renders get reaped and refunded rather than billed, which a DIY build does not do for you. And the TikTok side arrives already through platform review, which is the weeks a solo builder spends before posting anything.
moat: Execution quality Integrations what a moat is
tuned pipelines across four inference vendors, plus platform-review pain · no model or network of its own
Who has already built it
Starting from here is still vibecoding: the prompt is for when you want it exactly your way.
- ComfyUI (opens in a new tab) — Node graph for running open image and video models locally · the render pipeline without the hosted invoice.
- Wan2.2 (opens in a new tab) — Apache-2.0 open video model with image-to-video, the free stand-in for the hosted animation step if you own a GPU.
- Postiz (opens in a new tab) — Open-source social publishing · the scheduling and OAuth half, self-hostable, so you never touch the TikTok API yourself.
Do you agree?
The vote balance
Ancora nessun voto: il tuo è il primo.
Nessun voto ancora — il primo pesa.
