20259dcad0
- Add Honda client with static_general and video_general profiles - Add video QC capability using Gemini native video analysis (4 checks: visual_quality, brand_consistency, text_legibility, pacing_flow) - Add video_general profile assigned to all 8 clients - Extend session lifetime with MSAL silent token refresh (proactive every 45min + reactive on expiry), switch cache to localStorage - Re-enable OCR layout measurements for Amazon checks - Add scope boundary notes to all 6 Amazon checks to prevent cross- check penalization (locale errors isolated to logo_country only) - Relax margins left-alignment tolerance from 1% to 4% to account for logo lockup internal padding - Update brand guidelines DB with Amazon localization matrix and processed Dove PDF summary Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
91 lines
3.9 KiB
Python
91 lines
3.9 KiB
Python
import os
|
|
import sys
|
|
|
|
# Add parent directory to path to import shared modules
|
|
sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
|
|
|
|
from visual_qc_apps.flask_app_template import FlaskAppTemplate
|
|
|
|
class VideoVisualQualityApp(FlaskAppTemplate):
|
|
"""
|
|
Video QC - Visual Quality Check
|
|
Evaluates overall visual quality of video content including resolution,
|
|
colour grading, exposure, focus, and technical artifacts.
|
|
"""
|
|
|
|
def __init__(self):
|
|
prompt = """You are performing a visual quality-control check on a VIDEO marketing asset. You are watching the full video — analyse it across its entire duration.
|
|
|
|
VIDEO VISUAL QUALITY EVALUATION:
|
|
|
|
Evaluate the following aspects across the entire video:
|
|
|
|
1. RESOLUTION & CLARITY:
|
|
- Is the video sharp and clear throughout, or are there soft/blurry segments?
|
|
- Are there any visible compression artifacts (blockiness, banding, mosquito noise)?
|
|
- Is the resolution appropriate for the intended use (e.g. social, broadcast, digital display)?
|
|
|
|
2. COLOUR & EXPOSURE:
|
|
- Is the colour grading consistent throughout the video?
|
|
- Are there any unintended colour shifts between scenes/shots?
|
|
- Is the exposure appropriate — no blown-out highlights or crushed shadows?
|
|
- Do brand colours appear accurate and consistent?
|
|
|
|
3. FOCUS & STABILITY:
|
|
- Are key subjects in focus throughout?
|
|
- Is there any unwanted camera shake or instability?
|
|
- Are intentional focus pulls/transitions executed cleanly?
|
|
|
|
4. TECHNICAL ARTIFACTS:
|
|
- Are there any frame drops, stuttering, or judder?
|
|
- Are there any visible encoding artifacts (especially at scene transitions)?
|
|
- Are there any black frames, flash frames, or unintended blank sections?
|
|
- Any visible green-screen or compositing edge issues?
|
|
|
|
5. AUDIO-VISUAL SYNC (if audio is present):
|
|
- Does the audio appear to sync with visual elements (lip sync, sound effects, music beats)?
|
|
- Note: You may not be able to hear audio, but note if lip movements appear mismatched with expected speech timing.
|
|
|
|
STEPS TO EVALUATE:
|
|
1. Watch the entire video and note any visual quality issues
|
|
2. Pay special attention to scene transitions and the opening/closing frames
|
|
3. Check for consistency in colour and exposure across the full duration
|
|
4. Note any technical artifacts or quality drops at specific moments
|
|
5. Assess whether the overall visual quality meets professional marketing standards
|
|
|
|
DECISION CRITERIA:
|
|
- PASS (score 7-10): Video is sharp, well-exposed, consistent colour, no visible artifacts
|
|
- MODERATE ISSUES (score 4-6): Minor quality issues — slight softness, minor colour inconsistency, or small artifacts that most viewers would not notice
|
|
- FAIL (score 1-3): Significant quality issues — blurry footage, visible artifacts, colour shifts, frame drops, or technical problems that undermine the professional appearance
|
|
|
|
YOUR OUTPUT:
|
|
Format your response as JSON:
|
|
{
|
|
"visual_quality_check": "Pass" or "Fail",
|
|
"resolution_clarity": {
|
|
"assessment": "Sharp/Clear" or "Slightly soft" or "Blurry/Low quality",
|
|
"compression_artifacts": true or false,
|
|
"notes": "Details"
|
|
},
|
|
"colour_exposure": {
|
|
"colour_consistency": "Consistent" or "Minor shifts" or "Inconsistent",
|
|
"exposure": "Good" or "Slightly over/under" or "Poor",
|
|
"notes": "Details"
|
|
},
|
|
"stability_focus": {
|
|
"focus_quality": "Sharp" or "Occasionally soft" or "Poor",
|
|
"stability": "Stable" or "Minor shake" or "Unstable",
|
|
"notes": "Details"
|
|
},
|
|
"technical_issues": ["List any artifacts, frame drops, or technical problems found. Empty array if none."],
|
|
"video_duration_assessed": "Approximate duration of the video",
|
|
"explanation": "Detailed reasoning for the overall assessment",
|
|
"recommendations": ["List specific recommendations if applicable, else an empty array"]
|
|
}"""
|
|
|
|
super().__init__(__name__, prompt)
|
|
|
|
# Run the app if executed directly
|
|
if __name__ == "__main__":
|
|
app_instance = VideoVisualQualityApp()
|
|
app_instance.run()
|