main
response.parquet
image → text
Google
caption
Caption this image {file_path} using the following structure.
## Prompt Structure
Use this framework: Subject + Action + Style + Context
Subject: The main focus (person, object, character)
Action: What the subject is doing or their pose
Style: Artistic approach, medium, or aesthetic
Context: Setting, lighting, time, mood, or atmospheric conditions
No negative prompts: FLUX.2 does not support negative prompts. Focus on describing what you want, not what you don’t want.
Word order matters - FLUX.2 pays more attention to what comes first. Put your most important elements at the beginning:
Priority order: Main subject → Key action → Critical style → Essential context → Secondary details
Prompt length guidance:
Short (10-30 words): Quick concepts and style exploration
Medium (30-80 words): Usually ideal for most projects
Long (80+ words): Complex scenes requiring detailed specifications
main
Feb 27, 2026, 2:07 AM UTC
Feb 27, 2026, 2:10 AM UTC
16 rows
22491 tokens$ 0.0645
16 rows processed, 22491 tokens used ($0.0645)
completed
2 columns, 16 rows