name	transparent-bg
description	Produce a truly RGBA-transparent asset from a brief. Handles the
trigger_phrases	["transparent background","transparent png","rgba","alpha channel","no background","cutout","isolated"]

Transparent background

The problem (see research 13 + 04)

Almost every modern T2I VAE is RGB-only. Asking Imagen 3/4 or Gemini 2.5/3 Flash Image for a "transparent logo" triggers one of two failures:

Flat background — DALL·E 3, Stable Diffusion families render a white/gray background that must be matted.
Checkerboard as RGB pixels — Gemini/Imagen literally render the gray-and-white 8×8 tile pattern (because Photoshop screenshots in their training data show transparency that way). This is the "weird boxes" users report. It cannot be fixed by prompting.

Fix hierarchy (apply first that fits)

1. Route to a native-RGBA provider

Provider	Mechanism
`gpt-image-1` / `gpt-image-1.5`	API param `background: "transparent"` + `output_format: "png"` or `"webp"`
Ideogram 3 Turbo	Dedicated `/ideogram-v3/generate-transparent` endpoint; set `rendering_speed: "TURBO"` for Turbo tier
Recraft V3	native SVG output (alpha is trivial); rasterize if raster needed
LayerDiffuse on SDXL / Flux	In-diffusion-loop transparency adapter; better edges than post-matte

2. Post-process matte (for everything else)

Matting model	License	Strength
BiRefNet	MIT	Default choice 2026; best soft-edge handling
BRIA RMBG-2.0	CC-BY-NC-4.0 (hosted API for commercial)	Best overall quality
U²-Net	Apache-2.0	Legacy fallback
rembg	wrapper around U²-Net / BiRefNet	Easy CLI integration
SAM 2	Apache-2.0	For complex/multi-object scenes; 2-stage (segment → matte)

3. Difference matting (for semi-transparency: glass, hair, smoke)

Generate the same subject on pure-white background.
Generate again with same seed on pure-black background.
alpha = (white_version - black_version + 255) / 2 in luminance.
Works for true semi-transparent objects where rembg/BiRefNet produce hard-cutout artifacts.

4. Vectorize-and-drop (for flat marks)

Generate raster at 1024² on white background.
BiRefNet matte → K-means quantize to N colors → vtracer or potrace.
SVG has alpha trivially. Rasterize at target sizes with @resvg/resvg-js for RGBA PNGs.

Validation (never ship without)

Tier-0 alpha validator (see packages/mcp-server/src/pipeline/validate.ts):

1. Check PNG/WebP header has alpha channel type (RGBA, not RGB).
2. Reject if no pixels have alpha < 255 (it's opaque).
3. Reject if >5% of pixels have alpha ∈ [0.05, 0.95] AND FFT signature shows gray-tile band frequency (Gemini fake checkerboard).
4. Alpha coverage: subject pixels (alpha > 0.5) should occupy 30–85% of frame (sanity check).
5. Premultiplied-alpha check: no RGB values where alpha==0 (cleanup artifacts).

Prompt scaffold for fallback matting flow

Do not ask for transparency in the prompt. Ask for pure white:

[SUBJECT, concrete].
Centered, isolated, no surrounding context or props.
Solid pure white #FFFFFF background.
Clean silhouette with distinct outline.
No drop shadow, no ground plane, no reflection.
1:1 square, 1024x1024.

Then post-process with BiRefNet / BRIA.

Never do this

"transparent background" as a prompt to Imagen or Gemini (checkerboard result).
Trust output_format: "png" alone to produce alpha (PNG supports alpha, but the model has to emit it).
Algorithmic #FFFFFF → alpha=0 thresholding (loses anti-aliasing, creates jagged edges).
Post-resize RGBA with non-premultiplied alpha (dark fringes).

Output

transparent/
├── mark.png         # RGBA, validated
├── mark@2x.png      # optional high-DPI
├── mark.svg         # if vector path chosen
└── meta.json        # alpha_coverage, matting_method, validation_hash

Más de este repositorio

mismo repositorio

ui-mockup-prompt

MohamedAbdallah-14/prompt-to-asset

Translate a UI brief (a page, a screen, a single component, a feature) into a paste-ready prompt for Nano Banana Pro / gpt-image-2 / Ideogram / Flux 2 / Midjourney that produces a designer-grade mockup as visual inspiration — not pixel-spec UI, not AI slop. Use whenever the user asks for "imagine the X page", "mock up the Y screen", "give me a prompt for nano banana / gpt image 2 to design", "describe this UI for an image model", "draft a prompt for the designer to take inspiration from", or any time the agent needs to produce a UI image-gen prompt for a real product surface (pricing page, dashboard, settings, onboarding, mobile screen, marketing hero, single component). Be pushy — trigger even when the user says "design" without "prompt", or "show me what X could look like" — the agent should reach for this skill before hand-rolling a brief.

2026-05-0615

ui-mockup-prompt

MohamedAbdallah-14/prompt-to-asset

2026-05-0615

asset-enhancer

MohamedAbdallah-14/prompt-to-asset

Classify a software-asset brief (logo, app icon, favicon, OG image, illustration, splash, icon pack, transparent mark), route to the right image model, rewrite the prompt in the target model's dialect, pick an execution mode (inline_svg / external_prompt_only / api) based on what's actually available, and run the pipeline. Use whenever the user asks for any visual asset for a software product.

2026-04-2615

logo

MohamedAbdallah-14/prompt-to-asset

Generate a production-grade logo (primary brand mark). Returns RGBA PNG master + SVG vector + monochrome variant. Route by text-length and per-model ceiling. Strong-text models render multi-word and even paragraph-length wordmarks reliably; weak-text models composite SVG type post-render.

2026-04-2615

t2i-prompt-dialect

MohamedAbdallah-14/prompt-to-asset

Rewrite an asset brief into the exact prompt dialect of the target image model (OpenAI gpt-image-1, Google Imagen/Gemini, SDXL, Flux.1/Flux.2, Midjourney, Ideogram, Recraft). Handles negative-prompt translation, token budgets, transparency quirks, brand-palette injection, and text-in-image ceilings so that `asset_generate_*` submissions succeed on the first try.

2026-04-2615

asset-validation-debug

MohamedAbdallah-14/prompt-to-asset

Diagnose and repair asset-generation failures. Maps tier-0/1/2 validation codes (checkerboard, missing alpha, safe-zone violation, palette drift, garbled wordmark, low contrast) to concrete repair primitives (matte, inpaint, route change, seed sweep, composite). Applies a retry budget so Claude does not loop on hopeless regenerations.

2026-04-2115

name	transparent-bg
description	Produce a truly RGBA-transparent asset from a brief. Handles the
trigger_phrases	["transparent background","transparent png","rgba","alpha channel","no background","cutout","isolated"]

Transparent background

The problem (see research 13 + 04)

Almost every modern T2I VAE is RGB-only. Asking Imagen 3/4 or Gemini 2.5/3 Flash Image for a "transparent logo" triggers one of two failures:

Flat background — DALL·E 3, Stable Diffusion families render a white/gray background that must be matted.
Checkerboard as RGB pixels — Gemini/Imagen literally render the gray-and-white 8×8 tile pattern (because Photoshop screenshots in their training data show transparency that way). This is the "weird boxes" users report. It cannot be fixed by prompting.

Fix hierarchy (apply first that fits)

1. Route to a native-RGBA provider

Provider	Mechanism
`gpt-image-1` / `gpt-image-1.5`	API param `background: "transparent"` + `output_format: "png"` or `"webp"`
Ideogram 3 Turbo	Dedicated `/ideogram-v3/generate-transparent` endpoint; set `rendering_speed: "TURBO"` for Turbo tier
Recraft V3	native SVG output (alpha is trivial); rasterize if raster needed
LayerDiffuse on SDXL / Flux	In-diffusion-loop transparency adapter; better edges than post-matte

2. Post-process matte (for everything else)

Matting model	License	Strength
BiRefNet	MIT	Default choice 2026; best soft-edge handling
BRIA RMBG-2.0	CC-BY-NC-4.0 (hosted API for commercial)	Best overall quality
U²-Net	Apache-2.0	Legacy fallback
rembg	wrapper around U²-Net / BiRefNet	Easy CLI integration
SAM 2	Apache-2.0	For complex/multi-object scenes; 2-stage (segment → matte)

3. Difference matting (for semi-transparency: glass, hair, smoke)

Generate the same subject on pure-white background.
Generate again with same seed on pure-black background.
alpha = (white_version - black_version + 255) / 2 in luminance.
Works for true semi-transparent objects where rembg/BiRefNet produce hard-cutout artifacts.

4. Vectorize-and-drop (for flat marks)

Generate raster at 1024² on white background.
BiRefNet matte → K-means quantize to N colors → vtracer or potrace.
SVG has alpha trivially. Rasterize at target sizes with @resvg/resvg-js for RGBA PNGs.

Validation (never ship without)

Tier-0 alpha validator (see packages/mcp-server/src/pipeline/validate.ts):

1. Check PNG/WebP header has alpha channel type (RGBA, not RGB).
2. Reject if no pixels have alpha < 255 (it's opaque).
3. Reject if >5% of pixels have alpha ∈ [0.05, 0.95] AND FFT signature shows gray-tile band frequency (Gemini fake checkerboard).
4. Alpha coverage: subject pixels (alpha > 0.5) should occupy 30–85% of frame (sanity check).
5. Premultiplied-alpha check: no RGB values where alpha==0 (cleanup artifacts).

Prompt scaffold for fallback matting flow

Do not ask for transparency in the prompt. Ask for pure white:

[SUBJECT, concrete].
Centered, isolated, no surrounding context or props.
Solid pure white #FFFFFF background.
Clean silhouette with distinct outline.
No drop shadow, no ground plane, no reflection.
1:1 square, 1024x1024.

Then post-process with BiRefNet / BRIA.

Never do this

"transparent background" as a prompt to Imagen or Gemini (checkerboard result).
Trust output_format: "png" alone to produce alpha (PNG supports alpha, but the model has to emit it).
Algorithmic #FFFFFF → alpha=0 thresholding (loses anti-aliasing, creates jagged edges).
Post-resize RGBA with non-premultiplied alpha (dark fringes).

Output

transparent/
├── mark.png         # RGBA, validated
├── mark@2x.png      # optional high-DPI
├── mark.svg         # if vector path chosen
└── meta.json        # alpha_coverage, matting_method, validation_hash