“model quality”的搜索结果

使用fal.ai提供的修复模型改善照片和文档图像质量，处理模糊、噪点、人脸画质及旧文档修复，并可按图像状况和修复目标提出请求。

• 减轻图像模糊
• 去除照片噪点
• 改善人脸画质

Compare actual AI session costs with estimates for using only Haiku, Sonnet, or Opus. The skill reports savings amounts and percentages, helping teams assess model selection costs while leaving differences in answer quality and retries outside the calculation.

中文简介正在准备中。当前显示英语简介。

• Report model selection savings during cost reviews
• Check savings after changing model selection settings
• Use JSON results to enforce a savings threshold in CI

Use PathML for local pathology image research, from loading whole-slide images and splitting them into tiles to preprocessing and quality checks. Plan multiplex measurements, analyze spatial relationships between cells, and run model inference in bounded batches.

中文简介正在准备中。当前显示英语简介。

• Planning tile extraction from whole-slide images
• Reviewing preprocessing and image quality
• Validating multiplex measurements and spatial graphs

Explains how PluginEval combines structural checks and experimental model assessments into quality scores. Helps interpret low scores, identify improvement areas, set marketplace thresholds, and explain what evaluation badges actually represent.

中文简介正在准备中。当前显示英语简介。

• Investigating why a skill received a low score
• Improving descriptions that define when a skill should run
• Setting score thresholds for marketplace listings

Choose SGLang Diffusion settings for a specific model, GPU, and memory budget. Compare generation speed, memory use, and output quality to select command-line options, including CPU offloading, multiple GPUs, caching, and reduced precision.

中文简介正在准备中。当前显示英语简介。

• Choosing generation settings for a specific model and GPU
• Reducing GPU memory use to fit a memory budget
• Comparing performance settings across multiple GPUs

Have a different AI model review code, analysis, or documents against the original skill's stated requirements. Receive evidence-based findings and a comparison of agreement and disagreement, then decide which recommendations to accept.

中文简介正在准备中。当前显示英语简介。

• Getting a second opinion on substantial code changes
• Reviewing authentication and other security-sensitive changes
• Checking work before a bulk operation

Test marketing prompts against shared cases, score required content, prohibited phrases, and output format, and compare alternatives. Keep version history and diffs, use reusable templates, and check that prompt or model updates preserve output quality.

中文简介正在准备中。当前显示英语简介。

• Compare two prompts for ads, email, or social content
• Keep prompt versions and review changes
• Check output quality after prompt or model updates

Design a RAG pipeline that retrieves documents to support AI answers. Analyze document splitting, select embedding models and vector databases, and evaluate retrieval quality using test queries and known relevant documents.

中文简介正在准备中。当前显示英语简介。

• Designing a RAG system for internal documents
• Choosing how to split documents for search
• Comparing embedding models and vector databases

Evaluate AI models and agents on Google Cloud using test datasets and scoring criteria. Generate simulated user scenarios, analyze failures, and compare results across changes to guide improvements to prompts and code.

中文简介正在准备中。当前显示英语简介。

• Build evaluation datasets from conversation logs
• Generate simulated user scenarios
• Choose scoring criteria for responses and tool use

Evaluate AI agent outputs with code checks and model-based grading. Run repeated trials to measure reliability, compare prompts or models, and check whether changes reduce quality, with saved transcripts for reviewing the results.

中文简介正在准备中。当前显示英语简介。

• Comparing two prompts on the same test cases
• Checking quality after agent configuration changes
• Turning real failures into repeatable evaluation cases

Build a Three.js 3D model from an object or character reference image using code. The workflow develops shapes and materials in stages, compares rendered views with the reference, and guides corrections through quality checks.

中文简介正在准备中。当前显示英语简介。

• Rebuilding a photographed object as a browser-based 3D prop
• Creating a stylized character from a reference image
• Planning model parts, materials, and animation pivots

Design and improve prompts for language models, then test their accuracy and consistency. Create reusable templates, JSON output schemas that define response structure, evaluation criteria, and test cases while considering token use and model differences.

中文简介正在准备中。当前显示英语简介。

• Designing prompts for a new AI application
• Improving inconsistent model responses
• Defining JSON response formats

Inspect production AI agents in FailproofAI Cloud using the fp CLI. Review errors, run histories, quality scores, and usage, then manage issues, audits, user access, and scoped API keys for the team's deployment.

中文简介正在准备中。当前显示英语简介。

• Investigating failed agent runs
• Checking for drops in quality scores
• Running audits and triaging findings

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

中文简介正在准备中。当前显示原文说明。

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

中文简介正在准备中。当前显示原文说明。

Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating poor recall / FAR / PASS-NO_PASS metrics, auditing visual inspection pipeline quality, or running an RCA report for an AOI defect-detection model. Trigger phrases include "RCA on my ChangeNet model", "why is my AOI model failing", "audit ChangeNet predictions", "investigate FAR regressions", "root cause analysis on visual-changenet".

中文简介正在准备中。当前显示原文说明。

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

中文简介正在准备中。当前显示原文说明。

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

中文简介正在准备中。当前显示原文说明。

Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.

中文简介正在准备中。当前显示原文说明。

Pick an LM output format per (task x consumer x model) rather than by reflex: different formats carry different cognitive load (e.g. code-in-JSON makes the same model write worse code than plain-text+diff, while asking for prose when you need a typed object fails the other way). Use when designing or debugging an LM's output schema, choosing between plain text / diff / JSON / tool-call / grammar-constrained output, or when a model's quality drops after wrapping its output in a structured format.

中文简介正在准备中。当前显示原文说明。

Use when choosing between engines or models for an agent pipeline and the answer must come from measurement on your own data, not from marketing pages: speech recognition for meeting recordings, the model that turns a transcript into notes, the critic model that checks it. Runs every variant in an isolated container, measures time, cost per hour of input (USD and RUB, with price source and date) and quality (WER/CER and course terms for ASR; code checks plus a judge of a different model for LLM steps), writes results.json/csv and one static analytics page. Triggers on "бенчмарк", "сравни движки", "сколько стоит час записи", "какую модель взять для пайплайна", "benchmark the pipeline", "compare ASR engines".

中文简介正在准备中。当前显示原文说明。

Produce video with Moonvalley's Marey model family (Marey Realism v1.5) — a filmmaker-oriented, 1080p/24fps generative video model marketed as trained exclusively on licensed data. Use this skill when a task asks for Marey or Moonvalley specifically, when a brief demands brand-safe / legally reviewed AI video for commercial or studio work, or when the request needs Marey's director-style controls (camera trajectory, motion transfer, pose transfer, keyframing, reference conditioning). It covers what "commercially safe" really means versus the actual terms of service, access routes (Moonvalley web / Voyager, the fal API, ComfyUI), pricing, capability limits, prompt and reference strategy, where Marey fits production versus where other models win, iteration, and quality review. Do not use it for audio generation, for photoreal talking-head dialogue, or as a generic "best video model" default.

中文简介正在准备中。当前显示原文说明。

Move quality earlier in the development lifecycle. Covers dev/QA pairing patterns, Three Amigos sessions, TDD facilitation (Red-Green-Refactor), PR review checklists for testability, and Definition of Done with quality gates. Includes shift-left maturity model for team assessment. Use when: "shift left," "TDD," "dev-QA pairing," "definition of done," "testability," "quality culture," "QA in sprint planning." Not for: writing the unit tests themselves — use unit-testing; automated PR test-quality review at scale — use ai-qa-review; multi-quarter QA direction or roadmap — use test-strategy. Related: unit-testing, ai-qa-review, test-strategy.

中文简介正在准备中。当前显示原文说明。

Use when a model is served online (FastAPI, BentoML) or scored in batch, when changing how a model artifact is loaded or versioned, or when adding drift, quality or prediction monitoring and a rollout plan for a new model

中文简介正在准备中。当前显示原文说明。