Results for “visual-direction”

Provides a creative-direction layer for music videos and short-form edits, defining an angelcore/cloud-trance/hyperpop aesthetic with mood, color, light, and beat-synced editing grammar, and orchestrating video production skills into a pipeline.

Visual Prompt Tuning

Trains and fine-tunes vision models for object detection, image classification, and segmentation using Hugging Face Transformers on cloud GPUs, with automatic dataset validation and Hub persistence.

Evaluates text-to-image models on spatial relationship accuracy using the VISOR metric, separating object detection from spatial correctness to reveal biases like object priority and merging.

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

Refactor SwiftUI views toward small, explicit, stable view types with MV data flow, dedicated subviews, and correct Observation usage.

Flamingo: A Visual Language Model for Few-Shot Learning

Translates creative intent into technical cinematographic directives for Veo3, Kling, and Luma video models via muapi.ai.

Generates structured VGL JSON for Bria FIBO models, giving deterministic control over objects, lighting, camera, composition, and style instead of natural language prompts.

SNLI-VE: Visual Entailment Dataset

Define every visual attribute as structured VGL JSON for deterministic, reproducible image generation with Bria FIBO models, covering objects, lighting, camera settings, composition, and style.

画像を理解（被写体・テキストOCR・構図・色・UI構造の分析）し、結果を構造化して返すスキル。CC CLI は GLM-5.3 等の vision 非対応モデルで稼働中のため画像を直接視認できず、主ルート Gemini 2.5 Flash（scripts/api/gemini_vision.py・無料枠）と副ルート 4_5v MCP（analyze_image・Readが返すCDN URL）の2経路で分析し、CCは結果の構造化・比較・保存に専任する。 ユーザーが「画像見て」「この画像何が写ってる」「画像比較して」「スクショ見て」「画像分析して」「画像理解」「vision-analyze」と言った時、または /vision-analyze を呼んだ時にトリガー。 ※画像生成（image generation）は対象外（make-song / video-prompt-spec / demo-site-sales参照）。ピクセル修正（花鈿除去等）は remove-huadian の役割。楽曲分析は analyze-song / reverse-engineer-song。

Inspect screenshots, photos, diagrams, image paths, and image URLs when the task depends on visible content. Use when the prompt lacks actual image content, native inspection fails, or the user requests inspect_image; prefer the MCP tool, then the installed CLI.

Two-party working posture — user as director, agent as executor. Every fork, tradeoff, and taste choice is surfaced via batched AskUserQuestion with structural framing, a recommended default, and concrete previews when comparison is visual, so the human steers direction while the agent handles implementation. Eliminates the review-bottleneck (no giant diff to approve at the end — review is distributed across picks) and prevents codebase-understanding debt (the user remembers the architecture because they picked it). Use whenever the user invokes /duet, or says "work with me", "ask before", "check with me", "I want to decide", "don't assume", "human-in-the-loop", "co-author", "pair with me", "duet", or whenever a task clearly involves aesthetic, architectural, or irreversible strategic decisions — even without those exact words. Pair with the Duet output style to minimize cognitive load between picks.