Generate
Create a new video-to-video job
Manual
Prompt builder
Batch upload
Who is making this?
H
HarryO
OwenF
FentonSelect a user to continue.
Reference video
Drop reference video or photo
MP4 · MOV · JPG · PNG · max 200 MB
First frame preview
Mode
Single
A/B — two outputs
Batch
Model
Ivy
Fashion · editorial · portrait
Hollie
Product · commercial · studio
Length
5sec
1s10s20s30s
Output will match the length of your input video
Style
Voice · RVC
Ivy voice
Consistent · trained · auto-applied
Hollie voice
Consistent · trained · auto-applied
0
Video controls
50%
Low = closer to reference · High = more creative · Dancing sweet spot: 40–60%
7.0
80%
70%
75%
100%
Options
Face lock
Keep face consistent across all frames
Lip sync mode
Prioritise facial accuracy — for talking videos
Audio preserve
Carry original audio through to output
Background replace
Remove and replace the reference background
Auto-retry on failure
Requeue automatically if the job crashes
Pin a specific first frame
Generation starts from this exact image
Select a user before adding to queue.
Queue
Active and recent jobs
Running
dance_ref_01 → Ivy · cinematic realism
✓Generate
✓Upscale
✓RIFE
◉RVC
○Merge
RVC voice conversion
GPU 3 · 3090 · replacing audio track
~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
GPUs
GPU 1 · 5060 TiGenerating
VRAM 9.3 / 16 GB
Load 95%
GPU 2 · 5060 TiIdle
VRAM 1.2 / 16 GB
Load 2%
GPU 3 · 3090Post
VRAM 11.4 / 24 GB
Load 88%
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 · GPU control · thermal throttle
ComfyUI
Online
Port 8188 · responding
Cloudflare
Connected
Tunnel healthy
Failover
Standby
DO API reachable
2TB drive
Healthy
847 GB used
GPU 1 temp
71°C
Pause at 76°C · auto-throttle on
GPU 2 temp
34°C
Pause at 80°C · normal
Thermal throttle
GPU 1 · RTX 5060 Ti
Throttled · 71°C · running at 70% power
71°C
Temp
9.3 GB
VRAM
65%
Load
Auto-throttle triggers at 71°C — 5° below
Lower = cooler but slower jobs
Auto-kill
GPU killed automatically if temp hits the threshold. Current job is checkpointed first.
88°C
Auto-throttle
Notify
Reroute to cloud
GPU 2 · RTX 5060 Ti
Normal · 34°C
34°C
Temp
1.2 GB
VRAM
2%
Load
Auto-throttle triggers at 75°C — 5° below
Auto-kill
GPU killed automatically if temp hits the threshold. Current job is checkpointed first.
90°C
Auto-throttle
Notify
Reroute to cloud
GPU 3 · RTX 3090
Normal · 62°C
62°C
Temp
11.4 GB
VRAM
88%
Load
Auto-throttle triggers at 80°C — 5° below
Auto-kill
GPU killed automatically if temp hits the threshold. Current job is checkpointed first.
93°C
Auto-throttle
Notify
Reroute to cloud
GPU management
GPU 1 · RTX 5060 Ti
16 GB GDDR7 · Slot 1 · Generation
Throttled
Role
Live stats
Temp
71°C
VRAM
9.3G
Load
65%
⚠ GPU 1 is offline — jobs will not route to this card until restarted
GPU 2 · RTX 5060 Ti
16 GB GDDR7 · Slot 2 · Generation
Idle
Role
Live stats
Temp
34°C
VRAM
1.2G
Load
2%
⚠ GPU 2 is offline — jobs will not route to this card until restarted
GPU 3 · RTX 3090
24 GB GDDR6X · Slot 3 · All post
Post
Role
Live stats
Temp
62°C
VRAM
11.4G
Load
88%
⚠ GPU 3 is offline — post-processing paused until restarted
VRAM peaks today
GPU 1 · 5060 Ti
11.2 GB
of 16 GB peak today
GPU 2 · 5060 Ti
3.4 GB
of 16 GB peak today
GPU 3 · 3090
14.8 GB
of 24 GB peak today
Network
EE SIM router
GL.iNet Spitz AX · top floor
Network
5G
SignalStrong — −82 dBm
Ping14 ms
IP192.168.8.1
↓ 94
Mbps down
↑ 28
Mbps up
Data used this month
EE · resets 1st
4.2 GB
of unlimited
Cloudflare Tunnel
ai.northadapt.com · Zero Trust
TunnelHealthy
Latency8 ms
Requests today1,204
AuthZero Trust · 3 users
↓ 99.9%
Uptime 30d
↑ 0
Blocked today
Case 1 — Generation rig
Wired ethernet · SIM router
IP192.168.8.10
ComfyUIPort 8188 · responding
Router scriptPort 5000 · healthy
Last seenJust now
Case 2 — Post rig
Wired ethernet · SIM router
IP192.168.8.11
ComfyUIPort 8190 · responding
Post pipelineReady · 5080 idle
Last seenJust now
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
ComfyUI
Failover — DigitalOcean H100
Auto failover
Spin up cloud GPU if local is unreachable for 30s
Auto shut down
Kill cloud instance when local comes back online
Output paths
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 |