Subscore

ExperienceTesting methodology

Experience measures what it is actually like to use the video generator.

A generator can create good videos and still be frustrating when every attempt takes several minutes, videos regularly fail, or you need to click through too many screens just to start.

We check generation speed, failed attempts, how many steps it takes to create a video, and whether you can quickly retry a finished result.

4 evidence groups
4 scored tests

Experience is organized into 4 evidence groups. Each group contains one scored test: Speed, Failures, Ease of Use, and Regeneration.

How the Experience score is calculated

Every test gets a score from 0 to 10.

We multiply each test score by how much it counts. We then add all the points together to calculate the final Experience score.

Experience makes up 33% of the Video score.

The first three tests count slightly more than Regeneration.

The stored weights are 17, 17, 17, and 16. We convert them into the percentages below so readers can easily see how much each test counts. Experience makes up 33% of the Video score.

25.37%Speed
25.37%Failures
25.37%Ease of Use
23.88%Regeneration

Weighted evidence groups (combined 100%)Experience score33% of Video score

View exact calculation

Each test gets a score from 0 to 10. We multiply that score by how much the test counts. We then add all the points together.

Experience makes up 33% of the Video score. Video makes up 10% of the overall performance score.

Scored tests and weights

Scored test	How much it counts	See scoring
Speed	25.37%	View
Failures	25.37%	View
Ease of Use	25.37%	View
Regeneration	23.88%	View
Total	100%

How the score is calculated

Each test gets a score from 0–10
Test score × how much it counts
Example: 8 × 25.37% = 2.03 points
We do this for every test
We add all the points together
Final Experience score
Counts for 33% of Video

Example calculation

We multiply each test score by how much it counts. We then add all the points together.

Scored test	Test score	How much it counts	Calculation	Points added
Speed	8.00	25.37%	8.00 × 25.37%	2.03
Failures	8.00	25.37%	8.00 × 25.37%	2.03
Ease of Use	8.00	25.37%	8.00 × 25.37%	2.03
Regeneration	5.00	23.88%	5.00 × 23.88%	1.19
Final Experience score	—	100%	Add all points	7.28/10

Special cases

Not Applicable

If a test does not apply, we remove it and spread its weight across the remaining tests.

Unknown

If we cannot verify a result, the test receives a score of 0.

Manual adjustment

In rare cases, we may adjust a score when the calculated result is clearly unfair. We always record the reason.

Why Experience matters

AI video generation can be expensive and slow.

A platform may create a great-looking video, but that does not help much when every attempt takes 20 minutes or half the generations fail.

Failed attempts are especially frustrating when the app still uses your credits. You may need to pay again just to get the video you originally asked for.

Ease of use also matters because many people signing up for AI girlfriend apps are beginners. You should not need to understand complicated video software or search through several menus before creating your first clip.

Regeneration makes bad results easier to fix. Instead of setting everything up again, you should be able to quickly retry the video or create another version.

A good video generator should be fast, reliable, and simple enough that normal users can create a video without a tutorial.

What good Experience looks like

A high Experience score means videos generate reasonably quickly, failures are rare, the generator is easy to use, and finished videos can be retried. A lower score means videos take too long, attempts regularly fail, or creating one clip requires too many steps.

Main benchmarks

GoodTypicalWeak

Generation speed

2 min or less2 min 1 sec–5 minOver 5 min

Failed attempts

20% or less21–40%Over 40%

Steps to start

56–89+

Minimum useful standard

Speed: 2 min or less
Failures: 20% or less
Ease of Use: 5
Regeneration: Yes

Common red flags

Video generation regularly takes more than ten minutes
Failed attempts still use credits
Videos remain stuck without showing a clear error
Important controls are hidden or difficult to understand
Creating one video requires too many unnecessary steps
There is no quick way to retry a bad result

How we test Experience

We use a paid account and test the normal video-generation process available to users.

For Speed, we time 10 video generations. The timer starts when generation is submitted and stops when the finished video becomes available.

For Failures, we record how many of those 10 attempts fail completely, remain stuck, produce no video, or produce a completely unusable result.

For Ease of Use, we create three videos and count every required click or action from opening the generator to starting the generation.

Finally, we try to regenerate three finished videos.

This lets us compare how fast, reliable, and easy each generator is under normal use.

Limitations and edge cases

Generation speed can change depending on server demand, internet connection, video length, and the settings used.

One slow generation does not automatically mean the platform is slow. We use the median time from several attempts so one unusual result does not control the score.

A video can also take longer because it has a higher resolution or longer duration. We record the settings used so readers can understand the result.

Ease of use does not measure how attractive the interface looks. It measures how many required steps users need to complete before generation starts.

Regeneration can also work in different ways. Some apps retry the same setup, while others create a variation. We record what the button actually does and use Limited when important restrictions make it less useful.

Video quality, motion, and character consistency are tested separately under Video Quality.

Evidence groups

Experience has 4 evidence groups made up of 4 scored tests.

Speed measures how long the generator normally takes to finish a video.

Fast generation makes it easier to try new ideas and replace a bad result without waiting several minutes every time.

Speed

25.37%of Speed (25.37% total)

How long the generator normally takes to finish a video.

How we test

We time 10 video generations. The timer starts when we submit the generation and stops when the finished video is available. We use the median time. The median is the middle result after all 10 times are placed in order. This prevents one unusually fast or slow attempt from changing the score too much.

What counts

Processing time after pressing Generate
Time spent waiting in a generation queue
Time until the finished video can be played
Normal attempts made through the paid account

What does not count

Time spent writing the prompt
Time spent choosing the source image
Time spent downloading the finished video
A confirmed internet or platform outage
Time after the finished video becomes available

Result shown

95 seconds

Median generation time: 95 seconds

Scoring

Faster generation means a higher score.

Median generation time	Score
60 or fewer	10/10
61–120	8/10
121–300	6/10
301–600	4/10
601–1200	2/10
1201+	0/10

A median generation time of 95 seconds scores 8/10.

Evidence group 2 of 4

Failures measures how often a video-generation attempt does not produce a usable result.

A generator may be fast, but it is still frustrating when too many attempts fail or remain stuck.

Failures

25.37%of Failures (25.37% total)

How often a video-generation attempt does not produce a usable result.

How we test

We record the result of 10 video-generation attempts. An attempt is marked as failed when it shows an error, remains stuck, produces no video, or produces a completely unusable result.

What counts

An error message instead of a video
A generation that never finishes
A blank or corrupted video
A video that cannot be opened or played
A severely broken result that cannot reasonably be used

What does not count

A video we simply do not like
A prompt detail being missed
Minor visual problems
A finished video with weak motion
A slow attempt that eventually produces a usable result

Result shown

Failure rate: 20%

2 failed attempts out of 10

Scoring

Fewer failures means a higher score.

Failure rate	Score
0%	10/10
20%	8/10
40%	6/10
60%	4/10
80%	2/10
100%	0/10

A failure rate of 20% scores 8/10.

The exact failure rate is used between these points.

Evidence group 3 of 4

Ease of Use measures how many steps it takes to start creating a video.

A simple generator should let you move from opening the tool to starting generation without clicking through several confusing screens.

Ease of Use

25.37%of Ease of Use (25.37% total)

How many steps it takes to start creating a video.

How we test

We create three videos. For each video, we count every required click or action from opening the generator to starting the generation. We then calculate the average number of steps.

What counts

Opening the video generator
Selecting the character or source image
Entering the required prompt
Choosing required video settings
Pressing the final Generate button
Any other required action before generation starts

What does not count

Optional settings
Time spent waiting for the video
Downloading the finished result
Watching the finished video
Editing or regenerating afterward
Actions that only appear because the tester chooses an optional feature

Result shown

4 steps

Average steps to start: 4

Scoring

Fewer required steps means a higher score.

Average steps	Score
3 or fewer	10/10
4–5	8/10
6–8	6/10
9–12	4/10
13+	2/10

An average of 4 steps scores 8/10.

Evidence group 4 of 4

Regeneration measures whether you can quickly retry a finished video or create another version.

This can save time when the first result is broken or does not look how you expected.

Regeneration

23.88%of Regeneration (23.88% total)

Whether you can quickly retry a finished video or create another version.

How we test

We create three finished videos. We then try to regenerate each one through the normal controls. We check whether a new video is created and whether important restrictions affect the feature.

What counts

A Regenerate or Retry button
Creating another version from the same setup
Reusing the source image and settings
A new finished video being produced
The feature working through normal paid access

What does not count

Starting a completely new generation from scratch
Re-entering every setting manually
Regenerating only the source image
A button that returns the same finished file
An attempt that fails without producing another video

Result shown

Limited — 2 of 3 videos were regenerated successfully

Scoring

We use the result categories below.

Result	Score
Yes — all three regenerations worked	10/10
Limited — only some worked or important restrictions applied	5/10
No — finished videos could not be regenerated	0/10
Unknown	0/10

In this example, Regeneration scores 5/10.

Back to Video