Results for “vision-language”

Vision-language chat: VQA, captioning, image dialogue.

Generate image captions, answer visual questions, and perform image-text retrieval using BLIP-2's Q-Former architecture with frozen vision encoders and LLMs.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.

Runs the open-source LLaVA vision-language model for image understanding, captioning, visual question answering, and multi-turn image conversations, including setup, inference, and training guidance.

Fine-tune and deploy CLIP vision-language models for zero-shot classification, image-text retrieval, and embedding extraction with ONNX and TensorRT support.

Enables visual instruction tuning and image-based conversations using open-source vision-language models. Supports multi-turn image chat, visual question answering, and image understanding tasks.

NLVR2: A Visual Reasoning Benchmark for Natural Language

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

GLIP: Grounded Language-Image Pre-training

VILA: On Pre-training for Visual Language Models

Flamingo: A Visual Language Model for Few-Shot Learning

CogVLM: Visual Expert for Pretrained Language Models

COCO: Microsoft COCO: Common Objects in Context

DreamLIP: Language-Image Pre-training with Long Captions

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

SNLI-VE: Visual Entailment Dataset

Nocaps: Novel Object Captioning at Scale

CogAgent: A Visual Language Model for GUI Agents

Visual Prompt Tuning

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。

Build a visual sequence that proves, explains, and supports decisions.

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.

TextVQA: Towards Reasoning about Text in Images

Open-Vocabulary Object Detection Using Captions

Multimodal Few-Shot Learning with Frozen Language Models

Improved Baselines with Visual Instruction Tuning

Skeptical pushback on visual placement — both density and quality. Reads the annotated outline plus the visuals manifest and asks (a) whether the article hits the density target from editorial-principles-visuals.md, (b) whether each [VISUAL:...] earns its place, (c) whether sections without one would benefit. One revision pass on FAIL (BLOG_AGENT_VISUALS_REVISION_BUDGET, default 1).

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

Enables zero-shot image classification, image-text matching, and cross-modal retrieval using OpenAI's CLIP model, with code for semantic search, content moderation, and vector database integration.