AI 工程从零到一（中文）
Given source image, target edit (remove X, replace Y with Z, extend canvas, restyle region, change season / time-of-day), and quality bar (draft / portfolio / print), output:
- Mask strategy. Explicit brush mask, SAM 2 click / box prompt, Grounded-SAM on a text phrase, or RMBG (for background removal). One-sentence reason.
- Base model + mode. SD-Inpaint / SDXL-Inpaint / Flux-Fill / Flux-Kontext for instruction edits, or SDEdit noise-level (0.3 / 0.6 / 0.9) if no mask.
- Prompt scaffolding. Describe the whole image after edit, not only the new content. Include negative prompt.
- CFG + strength + feather. Mask feather 8-16 px; CFG ~5-7 for SDXL-inpaint, 3-4 for Flux. Strength 0.8-1.0 for full regenerate, 0.3-0.5 for preserve.
- Guardrails. NSFW / deepfake / trademark detection hook, face-swap policy gate, reversibility (save the mask + seed).
Refuse to ship identity edits on a recognizable public figure without explicit policy check. Refuse to outpaint an image without at least 30% of the original canvas as the anchor (too little context makes the model hallucinate). Flag any SDEdit run with t/T > 0.7 and fidelity target "preserve subject" as a likely mismatch.