Generate
Create a new video via TJP API
Single
Prompt builder
Batch
Who is this for?
H
HarryO
OwenF
FentonSelect a user to continue.
Reference video
Drop reference video
MP4 · MOV · max 200 MB
Model
Ivy
Fashion · editorial · portrait
Hollie
Product · commercial · studio
Mode
Single
A/B — two outputs
Style
Outfit
Background
Prompted
From library
Keep original
Video settings
80%
75%
Higher style intensity = stronger prompt adherence, less natural motion
Options
Face lock
Keep face consistent across all frames
Audio preserve
Carry original audio through to output
Background replace
Remove and replace the reference background
Strip metadata
Remove all AI tags and write clean device metadata on output
Estimated cost
Standard quality · 17 sec · TJP API
~12 credits
4,280 remaining
Select a user before submitting.
Queue
Active and recent jobs
Running
dance_ref_01 → Ivy · cinematic realism
✓Generate
✓Upscale
✓RIFE
◉RVC
○Merge
RVC voice conversion
TJP API · processing
~35 sec remaining13%
Running
Up next
talk_ref_03 → Hollie · cool editorialA/B · A
Ready in ~11 min
Next
talk_ref_03 → Hollie · cool editorialA/B · B
Ready in ~14 min
Pos 2
Completed
dance_ref_02 → Ivy · dramatic
Done
API status
TJP API
Online
84 ms response
Credits
4,280
Used 5,720 this month
Queue
3 jobs
1 processing · 2 waiting
Storage · 2 TB
847 GB used1,153 GB free
Harry — 312 GB
Owen — 284 GB
Fenton — 251 GB
Schedule
Set jobs to run overnight or at a set time
New scheduled job
Drop reference videos
All processed with the same settings
Scheduled
dance_batch_10 → Ivy · dramatic
talk_weekly → Hollie · warm studio
editorial_overnight → Ivy
Gallery
All generated outputs
47
Today
+6 vs yesterday
312
This week
1,204
All time
847 GB
On 2TB drive
0:17
dance_ref_01
A/B·A
0:05
talk_ref_03
A/B·B
0:05
talk_ref_03
0:30
dance_editorial
0:09
talk_warm_01
0:22
dance_hero_01
0:05
talk_ref_07
0:13
dance_cool_02
Compare
Side by side — pick the winner
Atalk_ref_03
Btalk_ref_03
Trim range
0:000:05
In: 0:00Out: 0:03
Ref library
Saved reference videos
dance_hip_hop_01
talk_direct_cam
dance_slow_01
talk_side_profile
Projects
Organise outputs into folders
September editorial
Dance content batch Q3
Talking head series — Aug
Templates
Saved job settings — one click to load
Quick dance draft
Full dance 30s high
Talking — lip sync
Overnight batch high
Health
System status · API connection · network
TJP API
Online
Responding · 84ms avg
Credits
4,280
Resets 1st Oct
Cloudflare
Connected
Tunnel healthy
EE SIM
5G
94 Mbps · strong signal
Queue
Running
3 jobs · 1 processing
Storage
Healthy
847 GB used
TJP API
Connection
api.tjp.com · authenticated
4,280
Credits left
84 ms
Avg latency
47
Jobs today
99.9%
Uptime 30d
5,720 credits used this monthResets 1 Oct
Network
EE SIM router
GL.iNet Spitz AX · top floor
Network
5G
Ping14 ms
Data used4.2 GB of unlimited
↓ 94
Mbps down
↑ 28
Mbps up
Cloudflare Tunnel
ai.northadapt.com · Zero Trust
Latency8 ms
Requests today1,204
AuthZero Trust · 3 users
99.9%
Uptime 30d
0
Blocked today
Analytics
Throughput, GPU hours, usage by user
47
Today
+6 vs yesterday
312
This week
1,204
All time
9.4 min
Avg per video
Last 7 days
GPU hours today
GPU 1 · 5060 Ti — Generation
4.7 hrs
39 jobs · 22 videos
GPU 2 · 5060 Ti — Generation
3.1 hrs
26 jobs · 15 videos
GPU 3 · 3090 — All post
2.2 hrs
47 post jobs · upscale + RIFE + RVC
Per user
Harry
22 videos
47% of today's output
Owen
14 videos
30% of today's output
Fenton
11 videos
23% of today's output
Train model
Fine-tune visual LoRA models and RVC voices
Train visual model — LoRA
Drop training images
JPG · PNG · min 20 images · 512px or larger · consistent style
Train voice — RVC
Upload 10+ minutes of clean speech audio. RVC training takes ~15 minutes. One voice per visual model — Ivy has one voice, Hollie has one voice.
Drop voice audio
WAV · MP3 · min 10 minutes · clean speech · no music
Your models
Ivy
Hollie
Your voices
Ivy voice
Hollie voice
Settings
ComfyUI endpoint, failover, users
TJP API
Low credit alert
Notify when credits drop below 500
Pause queue on low credits
Stop sending new jobs when below 200 credits
Output
Strip AI metadata
Remove all AI tags on every output automatically
Write device metadata
Replace with clean iPhone / camera metadata
Users
H
Harry
O
Owen
F
Fenton
Publer
Auto-schedule on approve
Approved videos go straight to Publer queue at the time you set
Auto-generate captions
Pre-fill caption with hashtags based on model and style
Notify on post
Send Discord/Telegram message when a video goes live
Power schedule
Auto power schedule
Both rigs wake and shut down automatically every day
Case 1 — Generation
2× RTX 5060 Ti
Complete current job before shutdown
Finishes the running generation, then powers off
Stop accepting new jobs at shutdown time
Queue pauses — no new jobs start after the cutoff
Case 2 — Post processing
RTX 5080
30 min after Case 1 — gives post time to finish
Drain post queue before shutdown
Finishes any remaining upscale / RIFE / RVC jobs then powers off
Hard cutoff at midnight
Force shutdown at 00:00 regardless — nothing runs past midnight
Today's schedule
08:00
Case 1 wakes · ComfyUI starts · queue opens
08:00
Case 2 wakes · post pipeline ready
22:00
Case 1 — queue closes · finishes current job · shuts down
22:30
Case 2 — drains post queue · shuts down
00:00
Hard cutoff — both cases off regardless
Outfit library
Saved outfit references for CatVTON — one click to apply
Red mini dress
Black crop top
White bikini
Pink tracksuit
Silver evening gown
Denim jacket + jeans
Floral sundress
Grey gym set
Background library
Saved backgrounds — static images and video loops
Warm studio grey
Rooftop sunset
Night city lights
Luxury bedroom
Soft pink gradient
Pool side
Miami beach
Dark neon grid
Publish
Organise, review and approve — videos go straight to Publer
Review queue
Bulk organiser
Scheduled
| Video | Caption | Platforms | Scheduled | ||
|---|---|---|---|---|---|
dance_ref_01 · Ivy |
18:00 Tue 9 Sep |
||||
talk_warm_01 · Hollie |
09:00 Wed 10 Sep |
||||
dance_editorial · Ivy |
21:00 Wed 10 Sep |
||||
dance_hero_01 · Hollie |
19:00 Thu 11 Sep |