Results for “image-text”

AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.

Generate high-CTR YouTube thumbnails with striking imagery, bold text placement, and emotional subjects using AI image generation.

Apply a text watermark to a photo using layer-based image composition for brand protection and copyright.

AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.

Generates article cover images with customizable type, palette, rendering, text, and mood dimensions, supporting multiple aspect ratios and backends.

AI image generation with OpenAI, Google and DashScope APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.

Three.js asset loading - GLTF, textures, images, models, async patterns. Use when loading 3D models, textures, HDR environments, or managing loading progress.

Generate a single continuous cinematic shot video with no cuts, using text or image prompts and configurable style, duration, and aspect ratio.

Generate artistic top-down photos of keyboard keycaps arranged to spell out custom text messages.

Creates ML demo interfaces with Gradio, supporting images, text, audio, and video inputs/outputs.

Text Claude from your phone — set up the njerschow/textme daemon so inbound iMessages drive a Claude Code session on your laptop, with voice notes, image input, code execution, and a phone-number whitelist.

Use when the user asks Codex to directly generate images with gpt-image-2 using inherited OpenAI/Codex-compatible environment credentials or local GPT_IMAGE2_* overrides, including text-to-image, reference-image guided generation, ratios, resolution, quality, variants, and saved local image files; run the bundled Node CLI and keep URL/sk configuration private.

Design Open Graph and social sharing images with platform-specific specs, text placement, and branding guidelines. Generate images via HTML-to-image or AI, and configure OG meta tags for Facebook, Twitter, LinkedIn, and more.

SynthText: Synthetic Data for Text Detection

Process and manipulate images using ImageMagick: resize, convert formats, batch process, and retrieve metadata.

Generate a front cover image with custom artwork, title text, and author attribution.

Convert an image between PNG, JPEG, and WebP formats with quality control for web optimization.

Creates a video intro frame with a typing cursor effect that reveals text character by character, accompanied by chromatic aberration trails and directional light leaks.

Generate Image (gemini / openai backends)

ImageNet: A Large-Scale Hierarchical Image Database

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.

|

Sigmoid Loss for Language Image Pre-Training

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Renders tweet content as a realistic X (Twitter) post card image for video overlays or image sharing, with interactive metrics and customizable themes.

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.

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

Generate or edit images with Codex. Use this skill whenever the user says "imagine ...", asks to create an image from a text description, transform or restyle an existing image, produce artwork / illustrations / logos / concept art, make image variations, or asks for any kind of AI image generation or image-to-image editing. All outputs are saved inside the current project's `./images/` folder by default.

Renders text or images as ASCII art for terminal-friendly output, including banners, frames, QR codes, and weather.

Writes Python and TypeScript code that calls the Gemini Interactions API for text generation, chat, multimodal understanding, image generation, streaming, research, function calling, and structured output, including migration from the legacy generateContent API.