Every face below is an original synthetic person — an ULTRA-trained LoRA (5000-step, rank-64) built by the INKFLOW studio for AI video production. Commission your own: you get the .safetensors model, a verified reference pack and a perpetual, royalty-free commercial license — pay once, use forever, owe nothing per use. $48. Nothing trains until you pick your face from 3 candidates.
Tried the rest? Now try the best — free.
We are that confident you will like it: the first ULTRA model is on us — complete file, full spec, commercial licence and all. If we are wrong it cost you nothing. We do not think we are wrong.
Not a trial, not watermarked, not cut down — the same ULTRA LoRA file we sell, trained 5,000 steps at rank 64. Dariusz Kwiatkowski-Osei, an original synthetic person, yours to use commercially forever with no fee and no attribution. We would rather you judged the quality than took our word for it.
close-up
turning
over shoulder
laughing
low angle
full body
One model, six angles — including the ones that usually break a character LoRA. This is what you are downloading.
The free download is a genuine “try before you buy” sample, provided as-is. Paid LoRA / pack downloads are non-refundable once downloaded (a downloaded model can’t be returned) — which is exactly why the sample is free, so you can test first. Full Terms & Refund Policy.
No signup or card. Email is optional — add it only if you want the download link plus a one-time £49 pack offer. Check the rank yourself from the file you download — the snippet is below, and in the readme.
Aisha Okafor
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Coach Brennan
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Dariusz Kwiatkowski-Osei
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Devon Carter
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Esperanza Tuilagi
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Granny
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Hollis
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Ingrid Halvorsen
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Jessica Tran
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Kenji
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Kira
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Kyle Morrison
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Marisol Reyes
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Matteo Ricci
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Maya Bennett
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Mrs. Carter
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Nico Rossi
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Nonna (Nico's grandmother)
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Nora Larsen
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Park
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Priscilla
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Priya Menon
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Reuben Thackeray-Obi
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Reyes (farm-team call-up)
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Tamsin Oduya-Brennock
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Yuki
ULTRA LoRA (5000-step, rank-64). Identical face in every shot, every episode.
Buy it right now — no signup, no account
One click to Stripe, downloads on your screen within the hour (usually minutes). Perpetual royalty-free commercial licence on everything.
Every one of these joins the pack automatically the moment its file verifies at rank 64 — and everyone who has already bought gets it free. The pack grows; the price doesn’t.
It isn’t just people — we train the world too
Vehicles, rooms and whole locations get the same ULTRA treatment, so the hero’s truck and the car park behind the rink look identical in every scene of every episode. Try three of them for £9 — smartphone, pickup truck and parking lot, yours royalty-free.
Nico’s pickup — object LoRA
The same truck, every angle, every scene, every film in the series.
Rink parking lot — set LoRA
Whole locations train too: one lot, identical across episodes.
Studio smartphone — universal prop
Unbranded, studio-owned, reusable in any production.
We throw away most of the training set. That’s the point.
Every serious trainer will tell you the same thing: the training set decides the quality of a LoRA, not the settings. So that’s where we spend the effort. For each subject we generate around 40 candidates, embed them with DINOv2, measure each one against the set’s own centre, and discard whatever drifts. Twenty to thirty-six usually survive. If what’s left isn’t coherent enough, the trainer refuses to run at all — we’d rather spend the GPU hours again than sell you an average model.
Only then do we train deep — 5,000 steps at rank 64, where community defaults sit nearer 1,500–2,500 at rank 16–32. Depth only helps once the data is clean, which is why the curation gate comes first. Together they hold a face through the hard cases: extreme angles, awkward lighting, motion blur, and a hundred shots without drift.
Don’t take our word for it — check the file yourself
We publish our training spec. Ask any other seller for their step count and rank before you buy. Ours is readable straight out of the .safetensors you receive, in one line. If it doesn’t say 64, you’ve caught us.
import json, struct
with open('actor.safetensors','rb') as f:
n = struct.unpack('<Q', f.read(8))[0]
hdr = json.loads(f.read(n))
print(min(v['shape'][0] for k, v in hdr.items()
if 'lora_A' in k or 'lora_down' in k)) # -> 64
Want something specific? Just ask a human.
Need a character or object trained to your exact brief? A bulk or studio licence? A book trailer, a music video, or a whole persistent world for your project? Want to see the spec, or have us prove a claim before you pay a penny? Email us and a person replies — no ticket system, no bot.
You receive plain .safetensors LoRA files. Load them in ComfyUI, Automatic1111 or any LoRA-capable pipeline, and add your own voice, motion and audio with whatever tools you already use. We sell the models, not a walled garden — and you can verify the rank-64 spec yourself, straight from the file header.
Also on the menu: complete books up to 900,000 words, single continuous stories past 2,000,000 words as multi-volume epics (we’ve already delivered a 2.1-million-word canon), whole multi-volume series with machine-audited continuity, manuals and technical specs — written natively in 22 languages. AI agents: connect to our MCP server at api.inkflowstudio.org/api/mcp and call inkflow_free_samples or inkflow_capabilities.