Test log
Pixlr test data
Raw results for the Pixlr review. The verdict is in the review.
- Tested
- 6 November 2026
- Tester
- Miles Foster
- Account
- Free demo account, signed up by RankDude, nothing paid to the brand
- Tests
- 10
- Screenshots
- 6
- Method
- Published methodology
- Environment
- Google Chrome on desktop
Results
| ID | Test | Key measurement | Score |
|---|---|---|---|
| T01 | Style Range | Styles run: 0 of 10 | n/a |
| T02 | Character & Subject Consistency | Images run: 0 of 12 | n/a |
| T03 | Editing, Inpainting & Image-to-Image | Edits run: 0 of 12 | n/a |
| T04 | Prompt Adherence | Elements correct: 42 of 43 | 5/5 |
| T05 | Photorealism & Anatomy | Images that pass: 3 of 4 | 4/5 |
| T06 | Text in Images | Words correct: 24 of 24 | 3/5 |
| T07 | Resolution & Upscaling | Native size: 1,024 px (1.05 MP) | 3/5 |
| T08 | Speed per Image | Median per image: 7.5 s | 5/5 |
| T09 | Usage Rights, Watermarks & Privacy | Points met: 4 of 8 checked | 2/5 |
| T10 | Pricing & Value | Free images: 10 | 4/5 |
| Overall (in the review) | 4/5 | ||
Style Range
n/aNot Tested- Method
- Ten style prompts for one lighthouse.
- Styles run
- 0 of 10
- Remark
- Not graded: no style prompt was run.
Raw notes
Ten style prompts for one lighthouse.
Not run: ten images cost 10 credits and the free account had 3 left after the other tests.
- Run on the next review of this tool.
Character & Subject Consistency
n/aNot Tested- Method
- A described woman and a described thermos in six scenes each.
- Images run
- 0 of 12
- Remark
- Not graded: no consistency prompt was run.
Raw notes
A described woman and a described thermos in six scenes each.
Not run: twelve images need 12 credits, and the free account had 3 left.
- Run on a plan with credits to spare.
Editing, Inpainting & Image-to-Image
n/aNot Tested- Method
- Twelve fixed edits.
- Edits run
- 0 of 12
- Remark
- Not graded: no edit was run.
Raw notes
Twelve fixed edits.
Not run: the credits were used up by the other tests.
- Run on a plan with credits to spare.
Prompt Adherence
5/5Tested- Method
- 7 of the 40 fixed prompts (2 portraits, 2 product shots, 2 set-wording images, 1 busy scene), typed in by script, first image kept, every written element counted at full size.
- Elements correct
- 42 of 43
- Busy scene
- 8 of 8
- Remark
- Scale 5: 90 percent or more of elements correct. The sample was 7 prompts and 43 elements, not 40 prompts and about 240, and only one of the six busy scenes.
Raw notes
7 of the 40 fixed prompts (2 portraits, 2 product shots, 2 set-wording images, 1 busy scene), typed in by script, first image kept, every written element counted at full size.
42 of 43 elements were right (97.7 percent). Portraits 12 of 12, products 11 of 11, the coffee shop sign and board 5 of 5, the kitchen scene 8 of 8.
The kitchen scene, the hard one, was perfect: three red apples left of a blue jug, the dog under the table, the cat on the chair and yellow curtains behind.
The one miss: the night market poster headline reads "Summer Night Night Market", so the headline element fails. Added content that changed the scene: an invented sign and a framed picture beside the coffee shop door.
- 7 of 40 prompts and one busy scene. The free credits ran out before the other five.
Photorealism & Anatomy
4/5Tested- Method
- Four portrait and product images (P1, P2, F1, F2), one run each, inspected at 100 percent for faults that give a generated image away.
- Images that pass
- 3 of 4
- Hand and face faults
- 0
- Remark
- Scale 4: 18 to 21 of 24 pass. The sample is 4 images, so 3 of 4 (75 percent) stands for 18 of 24.
Raw notes
Four portrait and product images (P1, P2, F1, F2), one run each, inspected at 100 percent for faults that give a generated image away.
Passed (3): the man on the bench, the laughing woman and the olive oil bottle, with no hand or face faults.
Failed (1): the left trainer carries a garbled embossed mark on its side instead of a clean logo.
Hand faults 0. Face faults 0. Faults in text-like marks on objects 1.
- Four images in one run, not 24 images in two runs.
Text in Images
3/5Tested- Method
- Two of the six set-wording prompts: the coffee shop sign and board (11 words) and the night market poster (13 words), 24 words in all.
- Words correct
- 24 of 24
- Images fully correct
- 0 of 2
- Remark
- Scale 3: the words alone would reach the top band, but the scale counts invented extra text as a fault and no image was clean, so I grade it 3.
Raw notes
Two of the six set-wording prompts: the coffee shop sign and board (11 words) and the night market poster (13 words), 24 words in all.
Every one of the 24 asked-for words was spelled right, in the place asked for.
Neither image was fully correct. The coffee shop picture added a second board with invented text ("Cosfaty Coffieern peet ao a jaKe."), and the poster headline repeats a word ("Summer Night Night Market").
Extra invented text counts as a fault, so 0 of 2 images are fully correct.
- Two of six prompts; the shop label, book cover, handwritten note and street sign were not run.
Resolution & Upscaling
3/5Tested- Method
- Every saved image was measured, one image was downloaded with the product's Download button and compared with the stored file, and one image was upscaled with Super scale at its largest setting (4x).
- Native size
- 1,024 px (1.05 MP)
- Upscaled size
- 4,096 px
- Remark
- Scale 3: 1 megapixel or more native and a soft upscaler. The size reaches the top band's 4,096 pixels, but the result is soft and rests on one crop.
Raw notes
Every saved image was measured, one image was downloaded with the product's Download button and compared with the stored file, and one image was upscaled with Super scale at its largest setting (4x).
All 7 images came out at 1,024 by 1,024 pixels (1.05 megapixels). The Download button gave the same file, JPEG, 228,162 bytes for the olive oil bottle.
Super scale 4x gave 4,096 by 4,096 pixels (16.8 megapixels) in 5.7 seconds, saved as a 530 KB JPEG. Compared at 100 percent with the original enlarged 4x, it is smoother but adds no new detail: the reflections in the glass stay soft.
A second pass was refused: "Image is already very large, this tool only works with smaller images."
- One upscale, not six. The 2K quality setting (2 credits) was not run.
Speed per Image
5/5Tested- Method
- Six of the seven generations were timed from pressing Generate to the image shown in the grid.
- Median per image
- 7.5 s
- Slowest image
- 7.7 s
- Remark
- Scale 5: a median under 10 seconds.
Raw notes
Six of the seven generations were timed from pressing Generate to the image shown in the grid.
Median 7.5 seconds, average 6.8, fastest 3.2, slowest 7.7.
The time stops at the 512 pixel preview in the grid; the 1,024 pixel file was there a few seconds later. The first image, made before the timer script existed, showed a 6 second timer and was on screen by 8 seconds.
No generation failed and there was no queue on the free plan.
- 6 timed generations, not 40, and timed to the preview, not the full-size file.
Usage Rights, Watermarks & Privacy
2/5Tested- Method
- The licence agreement and terms of use (read 6 November 2026) and the downloaded files were checked against the ten-point list.
- Points met
- 4 of 8 checked
- Remark
- Scale 2: 4 or 5 of 10. 4 of 8 checked is 50 percent, so about 5 of 10.
Raw notes
The licence agreement and terms of use (read 6 November 2026) and the downloaded files were checked against the ten-point list. Eight points could be checked on the free plan.
Met (4): commercial use is allowed on paid and on free ("You may use AI Content for personal and commercial purposes"); the terms say who may use the output; the free download had no visible watermark and was the same file as the stored image.
Not met (4): results open on a public community page and the Make private toggle is off by default, with private mode on Premium and private content on Ultra; no opt-out from training was found; no stated source for training data; no content credentials in the file bytes.
Also in the licence: You give Pixlr a "non-exclusive, sublicensable, worldwide, perpetual, royalty-free and irrevocable right" to reproduce and display your prompts and results.
Not tested (2): a watermark on paid downloads, and whether real people are refused when asked for.
- Terms read by me, not a lawyer. No paid plan was bought.
Pricing & Value
4/5Tested- Method
- The free tier was used until the credits were nearly gone, and the plans page was read in the monthly view.
- Free images
- 10
- Cost per image on Plus
- about $0.031
- Remark
- Scale 4: $0.02 to $0.049 an image. Plus is the cheapest plan that allows commercial use; the free 10 images are one allowance, with no stated daily reset, so the top band is out.
Raw notes
The free tier was used until the credits were nearly gone, and the plans page was read in the monthly view.
Free: 10 credits, one 1K image 1 credit, so 10 images. The pages I read do not say when the free credits reset, and the counter read 3 after 7 images and an upscale whose panel quoted 1 credit.
The cheapest plan is Plus at $2.49 a month for 80 credits, about 80 fast images: $0.031 an image. Premium is $9.99 for 1,000 credits and Ultra starts at $24.99.
Costs on top: 2 credits for a 2K image and about 5 for a pro-model image (16 pro images on Plus). Private mode needs Premium and private content Ultra. Trustpilot showed 2.0 out of 5 from 186 reviews on 6 November 2026, with complaints about charges, auto-renewals and disappearing credits.
- No plan bought; the yearly prices and the credit reset were not read.
Coverage
Tested
- 7 of the 40 fixed prompts, first image kept: 2 portraits, 2 product shots, 2 set-wording images, 1 busy scene
- Time of 6 of the 7 generations and the credit balance
- One 4x Super scale upscale, compared with the original at 100 percent
- The product's own Download button, compared with the stored file
- Terms of use, licence agreement and plans page read in full
Not tested or limited
- The free plan's 10 credits paid for 7 images and an upscale: 7 of the 40 prompts were run
- Style range, consistency and editing were not graded: no credits were left and the reference and edit features were not run
- Photorealism used 4 images from one run, not 24 from two runs; resolution used one upscale, not six
- Speed times stop at the 512 pixel preview in the image grid; the 1,024 pixel file follows within seconds
- No plan was bought: paid privacy, the paid file set and cancellation were not tested; the free credit reset is not stated on the pages read
- Prompts naming real people or brands were not run, so the enforcement point of the rights checklist was not tested
Still to test
- Style range, consistency and editing on a paid plan
- Photorealism with 24 images, and the other 33 prompts
- The larger models (5 to 65 credits) and 2K quality
- Private mode, the free credit reset and cancellation after buying Plus