2026-04-21T14-37-10Z__iter_02
4/21/2026, 2:37:10 PM · 1 flow · 8,321ms total
clean All settings match production defaults (app_defaults.yaml asOf 2026-04-19).
Build provenance
App
1.4·3
com.flashcopy.app.dev
Git
9000297eac
feature/ocr-v2-structured-lambdas
Sim
AAC26DF1…
com.flashcopy.app.dev
Built at
4/21/2026, 1:54:04 PM
single-photo
Input media
No media file found for this input.
notepad_picture.JPG2.16 MBsha256 e1930563e9…
Input id
AAAA0004
Total
8.32s
Output
78 words
403 chars
Cost est
$0.00006
gemini-2.5-flash · basis: chars
in 433 · out 101 tok
Stage timings
local-vision
1.22s
moderation
489ms
s3-upload
1.64s
gemini-ocr
4.97s
Stage details
| local-vision | regions 20 conf 0.975 |
| moderation | lambda moderation_ocr_v2 approved true |
| s3-upload | bucket qr-uploads-sup key incoming/cdaba3f9-c3c1-4a55-ade3-7d59018f4e05.jpg |
| gemini-ocr | lambda moderation_ocr_v2 model gemini-2.5-flash |
Extracted text
78 words · 403 chars
These are all the cool things
you can do with Flash Copy!
Flash Copy can:
Scan & process a page of text in seconds!
It doesn't even matter if it's cursive!
It can copy a list
1. Step 1
a. Step 1-a
b. Step 2-a
2. Step 2
a. Step 2-a
b. Getting the picture now?
It can copy code as well!
def hello World():
print ("Hello World")
print ("Thanks for reading!")
# Python comment here
return TrueRaw Gemini response (v2)
parseable 465 chars — click to expand
{
"ocr_text": "These are all the cool things\nyou can do with Flash Copy!\n\nFlash Copy can:\n\nScan & process a page of text in seconds!\nIt doesn't even matter if it's cursive!\n\nIt can copy a list\n\n1. Step 1\na. Step 1-a\nb. Step 2-a\n2. Step 2\na. Step 2-a\nb. Getting the picture now?\n\nIt can copy code as well!\n\ndef hello World():\n print (\"Hello World\")\n print (\"Thanks for reading!\")\n # Python comment here\n return True",
"notes": ""
} Prompts used
all prompts → photo_ocr gemini-2.5-flash 48496a3017… · 699 chars
Can you please OCR this image? Please OCR and do not modify the content and try and generate the OCR result with the same exact formatting as the input image. Please focus in ensuring the OCR process flawlessly retains the source's formatting. I aim to go line-by-line, capturing every detail, including special characters, comments, and those crucial line breaks, indentations, and case differences, thus guaranteeing the output mirrors the original. However, please remove any items from an editor or parts of the IDE/word processor that are shown in any potential screenshot to as just show only the content instead. (For instance removing the list of windows open/ line numbers, file name etc.)
qr_reader_v1/EXTENDED_LAMBDA_OCR.py:108
Output diff
vs 2026-04-21T14-36-07Z__iter_01 Diff+0 words−0 words=78 unchanged·100.0% similar (by char)(prior run 2026-04-21T14-36-07Z__iter_01 → this run)
These are all the cool things
you can do with Flash Copy!
Flash Copy can:
Scan & process a page of text in seconds!
It doesn't even matter if it's cursive!
It can copy a list
1. Step 1
a. Step 1-a
b. Step 2-a
2. Step 2
a. Step 2-a
b. Getting the picture now?
It can copy code as well!
def hello World():
print ("Hello World")
print ("Thanks for reading!")
# Python comment here
return TrueRun settings
Show all 20 values
{
"videoFramesPerSecond": 1,
"videoStitchingMethod": "gemini_only",
"videoPipelineMode": "s3_parallel",
"useBackgroundVideoProcessing": true,
"rekognitionThreshold": 80,
"geminiModel": "gemini-2.5-flash",
"photoOcrPromptSha": "48496a3017a2708a92d142281c5ab19f64f8132555514a00cbc35ca9d39daeba",
"frameOcrPromptSha": "66326cc5be6bdd434dbbdd330b519e26bd8bbcab4a6037a64c2148b66cd2aceb",
"imageRetentionHours": 24,
"bypassImageSaveConfirmation": true,
"bypassProcessingResultWindow": true,
"enableAnalytics": true,
"confirmCollectionReset": true,
"enableNotifications": false,
"autoProcessImages": true,
"includeBrandingInSharedText": true,
"autoSavePhotos": true,
"multiPhotoSeparator": "double_line",
"showDebugInfo": false,
"headerFooterStyle": "equals"
}