A manual Photoshop method for faking 3D depth information in flat 2D text/shapes so that Firefly's composition-reference shape detection interprets them as three-dimensional rather than flat. Needed because a flat, single-color 2D shape (typical for text/letterforms) generates a flat-looking Firefly result — Firefly's detector otherwise reads adjoining same-colored regions as one merged blob. Not needed for simple shapes like emoji, which can be uploaded directly.
Steps:
Related fixes in the same pipeline: if Firefly generates a texture (e.g. sand) that fails to visually merge with the shape, painting a solid color block over that area in Photoshop before re-exporting helps the material apply correctly — implying Firefly's material application can fail to saturate a shape unless the reference itself is solidly filled in that zone. Background elements (e.g. a horizon/floor) are built with the Rectangular Marquee tool plus a non-destructive Solid Color adjustment layer above the background layer, so the floor color stays editable at any time.
None — new concept, no prior vault coverage of manual shape-detection workarounds for AI image composition tools.
Из тем: Beyond Photoshop: Other Tools & Prompting Techniques