-
1
Start with the intended image job: product landscape, social cover, pin concept, reference frame, campaign visual, style study, or image-to-video source frame
-
2
Choose nano-banana-pro when the searcher names Nano Banana Pro, then compare gpt-image-2, doubao-seedream-4-5, doubao-seedream-5-0-lite, or wan2.7-image when the brief needs another still-image route
-
3
Write the prompt as an image brief with subject, composition, camera distance, lighting, aspect ratio, color range, texture, brand fit, reuse context, and review notes
-
4
For image-to-image work, record what the reference image is allowed to control: layout, palette, mood, object position, material, or background direction
-
5
Review outputs for text accuracy, artifact density, protected-character similarity, real-person likeness risk, sensitive context, and whether the image can become a clean source frame
-
6
If motion is useful, send only the reviewed still image to Seedance 2.0, Seedance 2.0 Fast, Wan 2.6 I2V, or Wan 2.6 T2V after the image passes review
-
7
Save the model label, prompt version, reference-image notes, rejected-output reason, and downstream video handoff decision before publishing or reusing the image