Try one for free!
Every face below is an original synthetic person — an ULTRA-trained LoRA (4,500+ 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 4,500+ 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.
Also free
Write the first three chapters of a book, free
The models above are half of what this studio does. The other half writes books — and the free plan writes a complete opening: three chapters, your story, your characters, no card.
Start writing free — 3 chapters10,000 AI words included. Export DOCX, EPUB or PDF and keep whatever you write.
licence & how to use itThe free download is a genuine “try before you buy” sample, provided as-is. Paid LoRA / pack downloads are non-refundable once downloaded (a pack we fail to deliver is refunded in full, and faulty files are replaced; 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 £48.99 pack offer. Check the rank yourself from the file you download — the snippet is below, and in the readme.
Coach Sullivan
ULTRA LoRA (4500-step, rank-64). Identical face in every shot, every episode.
Hollis
ULTRA LoRA (4500-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.
Maya Bennett
ULTRA LoRA (4500-step, rank-64). Identical face in every shot, every episode.
Nonna (Nico's grandmother)
ULTRA LoRA (4500-step, rank-64). Identical face in every shot, every episode.
Nora Larsen
ULTRA LoRA (4500-step, rank-64). Identical face in every shot, every episode.
Priscilla
ULTRA LoRA (4750-step, rank-64). Identical face in every shot, every episode.
Priya Menon
ULTRA LoRA (4500-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.
Pack prices
World Pack: £28.99 — and it comes free with the Cast Pack.
Cast Pack: £48.99 (about $62) for every actor on the shelf, with the whole World Pack included.
In the oven right now: 30 more ULTRA models
Desmond Achterberg · Desmond Achebe-Walsh · Dagmar Solberg-Osei · Celestine Beaumont-Oduya · Teodoro Vaszquez-Mwangi · Themba Vorster · Bremley Achach · Tariq Osei-Marchetti · Reuben Ostrovsky-Nakamura · Bertrand Achille Mouamba · Tevita Sørensen · Bemnet Tsegaye-Holt · Reuben Achterberg · Reuben Tcharkhoutian · Tomasz Wierzbicki-Nakamura · Tariq Osei-Vásquez · Teodoro Mbeki-Vásquez · Rufus Delacroix-Papadopoulos · Tomás Vreeland-Achebe · Reuben Mwangi-Castillo · Themba Vreeland · Branimir Solčić · Tenzin Wulfhart · Tariq Osei-Belmont · Tariq Mehrzad-Okonkwo · Feroz Salahuddin · Bertrand Osei-Nakamura · Babatunde Osei-Mirzoyan · Radovan Petrescu · Rajiv Subramaniam-Wolfe
Everything listed here — shelf models now, in-training models the moment they verify at rank 64 — is part of the pack you buy today. Future themed collections may be sold separately.
Watch a complete film made with this catalogue
A full music-video film, every face and place from the pack: 14 ULTRA LoRAs — 7 characters, led by Aisha Okafor and Nico Rossi, and 7 trained sets & props. The same faces hold from first frame to last — that is the product, on screen. It is also a book trailer: the story is adapted from the ice-hockey romance “Checking the Rules”, written by this studio — the cast you can buy, acting the book we wrote. The film carries its AI-generated disclosure badge.
⛶ Expand — watch the full-screen high-res version · Aisha and Nico are in the Cast Pack below. The bar, the rink, the phones — all in the World Pack.
RealLife
3 ULTRA LoRAs from this catalogue in one film — every one is in the pack below. AI-generated, disclosure badge burned in.
Bird's Eye View
4 ULTRA LoRAs from this catalogue in one film — every one is in the pack below. AI-generated, disclosure badge burned in.
Emotion Motion
4 ULTRA LoRAs from this catalogue in one film — every one is in the pack below. AI-generated, disclosure badge burned in.
Watch Di Ride - Forge Line Brawl (hockey)
10 ULTRA LoRAs from this catalogue in one film — every one is in the pack below. AI-generated, disclosure badge burned in.
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.Grab the one-image contact sheet of the whole world pack — save it, share it. Below is every trained set and prop in the pack today — everything listed - including items still in training - is included in the pack. Starter taste: smartphone, pickup truck and parking lot for £8.99, royalty-free.
Nico's truck
The same truck, every angle, every scene, every film in the series.
The rink
The home arena — same ice, boards and glass in every episode.
Aisha's apartment
A home set — same kitchen, same light, whole series.
Forge locker room
The dressing room set — persistent down to the stall plates.
Coach Brennan's office
The coach’s office — persistent shelves, desk and blinds.
Press box
The stadium press box — one geography, every match.
The bar
The friends’ bar — same booths, brick and neon, every visit.
Inside Nico's truck
The same truck, every angle, every scene, every film in the series.
Rink parking lot
Whole locations train too: one lot, identical across episodes.
Priya's apartment
A home set — same kitchen, same light, whole series.
Aisha's press credential / lanyard
A wearable prop — same credential on every cut.
Aisha's parking spot (Spot 14)
A single numbered parking spot, findable in every episode.
digital recorder
A hand prop that stays the same device in every hand.
Nico's apartment kitchen
A home set — same kitchen, same light, whole series.
the serving spoon
Proof that even the smallest prop can hold its identity.
Arena press room
The arena press room, persistent wall to wall.
studio smartphone
Unbranded, studio-owned, reusable in any production.
city newsroom
A working city newsroom — desks, screens and clutter held constant.
press conference room
Backdrop, mics and podium — consistent across pressers.
Hospital ward
A hospital ward that stays the same ward all season.
City street (day)
A city street in daylight — same shopfronts every take.
bookshop interior
A warm bookshop interior with persistent shelves and stock.
diner interior
A classic diner interior that never redecorates itself between shots.
laundromat interior
Row of machines, strip lighting — identical every scene.
grocery store interior
A persistent studio prop — the same object in every shot.
taxi cab
A persistent studio prop — the same object in every shot.
city bus
A persistent studio prop — the same object in every shot.
taxi cab interior
A persistent studio prop — the same object in every shot.
city bus interior
A persistent studio prop — the same object in every shot.
laundromat interior (night)
Row of machines, strip lighting — identical every scene.
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 — 4,500+ 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)) # -> 64Want 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.
[email protected]🔓 Yours to own — no wrapper, no runtime
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.
Questions buyers actually ask
Can I use these commercially?
Yes. Every purchase (and the free sample) carries a perpetual, royalty-free commercial licence: pay once, use forever, no per-use fee and no attribution required.
What do “4,500+ steps” and “rank 64” actually mean?
Training depth and model capacity. Community LoRAs typically train 1,500–2,500 steps at rank 16–32; ours train 4,500+ steps at rank 64 on a curated set, which is what holds one face steady through extreme angles, hard lighting and motion blur. Both numbers are readable straight from the .safetensors header — the one-line check is published above.
Are downloads refundable?
Paid LoRA and pack downloads are non-refundable once downloaded (a pack we fail to deliver is refunded in full, and faulty files are replaced). A downloaded model cannot be returned. That is exactly why the full free sample exists: test everything before you spend a penny.
What exactly is included when I buy?
Everything listed on this page at the time you buy - shelf models immediately, in-training models when they verify. Future themed collections (style worlds, regional packs) may be released as separate packs.
Can I verify the quality before paying?
Yes, completely. Download the free ULTRA model — the same file class we sell, no signup — render with it, and read the rank out of the file header with the snippet above. If it doesn’t say 64, you’ve caught us.
The studio also writes complete books
Not a promise — a delivery record: one continuous canon of 2,138,487 words across 14 volumes (773 chapters) has already been written, with a single continuity ledger holding it together — the first series alone runs 1,254,473 words and crossed the 900,000-word mark with continuity intact.
Full-length novels, series and technical manuals up to 900,000 words — any genre, written natively in 26 languages, delivered autonomously by the same engine that has already shipped a 2.1-million-word continuous canon with machine-audited continuity. Describe the book, pay, download; a typical novel arrives in under 24 hours.
Order a complete bookAlso 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 26 languages. AI agents: connect to our MCP server at api.inkflowstudio.org/api/mcp and call inkflow_free_samples or inkflow_capabilities.
