Use cases · AI influencers
An AI influencer with the same face
Photos from reference images so the character stays the same, talking videos from one portrait and a voice, captions on every post. A daily feed has a price you can check before you render it.
From $2.19 per piece at current prices
What you can make
- A consistent character in new outfits, places and poses
- Photo carousels for Instagram and TikTok
- Talking videos with a voice that stays the same
- Short motion clips from a still with Kling v3
- A month of posts planned and rendered in one batch
The pipeline
- 1
Reference set
Pick or generate a few portraits of the character. Every later image passes them as identity references.
- 2
Photos
Nano Banana renders each new scene with the same face; FLUX.2 [pro] or Seedream for other looks.
- 3
Voice and video
An ElevenLabs voice reads the caption and the avatar model turns a portrait into a talking video.
- 4
Motion and captions
Kling v3 animates a still into a short clip, then captions go on and the post is exported.
Cost per piece
Each line is a real row of the rate table at the public prepaid price, multiplied out. A range means the price depends on something only the run decides, such as the length of the text. Each job shows what it actually cost.
One daily post: 4 photos and a 15 second video
Photos with identity references, avatar video billed per second.
A month of daily posts (× 30): $65.66–$66.52 at current prices.
Every rate, machine-readable: GET /api/pricing
Run it from Claude Code
Connect the hosted MCP server once, then describe the batch in plain words. Claude plans it, calls the models, waits for each render and hands you the files with what they cost.
claude mcp add --transport http aitachyon \
https://aitachyon.com/api/mcp \
--header "Authorization: Bearer ait_..."“Using Mia's four reference photos, make this week's posts: four Nano Banana photos of her in Lisbon each day and a 15 second talking video where she says what she is up to, with her usual ElevenLabs voice. Captions on the videos.”
Or from your code
Plain HTTP with a bearer key. Video returns a job you poll; every file carries a ref you can fetch later with GET /api/generations/{ref}.
curl https://aitachyon.com/api/images/generate \
-H "Authorization: Bearer ait_your_key" \
-H "Content-Type: application/json" \
-d '{"projectId":"<project id>","prompt":"Mia at a cafe window in Lisbon, candid, morning light","provider":"nanobanana","referenceMode":"identity","referenceImageIds":["<image id>","<image id>"],"width":1024,"height":1280}'Built for volume
- Pay per call from a prepaid dollar balance that never expires
- A failed render is refunded to your balance automatically
- Per-key spend, alerts and one-click revoke, so a runaway script stays contained
- Every file has a ref you can fetch with GET /api/generations/{ref}
- The web studio, the HTTP API and the MCP server share one account and one balance
Platform rules you need to respect
Generating is the easy part. What you publish is your responsibility, and each platform has rules for AI content. Never present an AI person as a real customer, a real review or a real event.
YouTube
Monetized channels are reviewed for inauthentic content: mass-produced or repetitive videos without real value added. Realistic altered or synthetic content has to be disclosed when you upload.
TikTok
Realistic AI-generated content has to carry a label, set with the AI-generated content toggle when you post. TikTok may also label it automatically.
Meta (Facebook, Instagram)
Meta labels content it detects as AI-made and asks you to disclose photorealistic video and realistic audio created or altered with AI. Ads about social issues, elections or politics have their own disclosure rules.
Policies change: read the current version before you publish. We make the files; we do not promise monetization, reach or views.