Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Where the Kami Still Walk
PromptsAncient Japanese village at night, quiet and empty, deeply spiritual atmosphere. Traditional wooden houses lining a narrow stone street, wet from recent rain, reflecting soft warm paper lantern light. Low mist drifting…
-
Underwater Veo 3 video
PromptsUltra-realistic 6-second cinematic underwater video: A sleek predator fish darts through a vibrant coral reef, scattering a school of colorful tropical fish. The camera follows from a low FPV angle just behind the…
-
Surreal Portrait — دو دلم
PromptsSurreal dreamlike portrait of an Iranian woman, face split by two different light sources (cold blue / warm amber), floating dust particles. Her brows work in opposite directions — one raised, one lowered — eyes not…
-
IBM: Granite 4.2 8B
ModelsGranite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...
ibm-granite/granite-4.2-8b -
Pixel Art Prompt Generator
PromptsAct as a Pixel Art Prompt Generator. When the user provides a subject, scene, character, object, or idea, generate a detailed image-generation prompt using the following style: - Chunky low-resolution pixel art - Thick…
-
AI Provider Research Expert
Prompts**Role & Objective:** You are an expert AI Infrastructure Research Analyst. Your task is to gather highly accurate, real-world data regarding a specific AI inference provider's free-tier and low-cost offerings. You…
-
AionLabs: Aion 3.5 Mini
ModelsAion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...
aion-labs/aion-3.5-mini -
Anthropic: Claude Sonnet 5
ModelsSonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
anthropic/claude-sonnet-5 -
Hiperrealista
PromptsA hyper-realistic close-up portrait (8K resolution) of a person's head and upper neck, captured from a slightly low angle. Use the uploaded image as the facial reference: the face must match exactly (100%), preserving…
-
role: Cheerful, practical kids' party planner who designs safe, age-appropriate birthday parties that are fun for children and low-stress for parents task: > Turn my notes about the child, the guests, the venue, and…
-
claude-terse
PromptsFor those who struggle with how Claude speaks to them. No more essays. No more slogans, metaphors, "it's not X, it's Y". This plugin makes Claude speak normally.
git clone https://github.com/lowenbjer/claude-terse.git -
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...
anthropic/claude-sonnet-5:batch -
Ultra-realistic cinematic studio portrait of a stylish man wearing thin round metal eyeglasses, minimal navy blazer over a black crew-neck shirt. Shot from a slightly low angle with confident, thoughtful expressions…
-
Gothic Lace Red Halo Portrait
PromptsOverall Composition & Camera Angle: A cinematic three-quarter profile portrait of a woman sitting with her back toward the camera, looking over her shoulder. Shot from a slightly low angle, emphasizing the dramatic…
-
Before and after reviews
PromptsA split before-and-after realistic skincare review photo of a ${age}-year-old Pakistani ${woman/girl}, extreme close-up shot focused on ${FOCUS AREA, e.g., lower cheek and jawline / chin / t-zone} showing authentic…
-
SpaceXAI: Grok 4.20
ModelsGrok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...
x-ai/grok-4.20 -
OpenAI: GPT-5.2 Chat
ModelsGPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning to selectively “think” on...
openai/gpt-5.2-chat -
OpenAI: GPT-5 Nano
ModelsGPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...
openai/gpt-5-nano -
OpenAI: GPT-4.1 Nano
ModelsFor tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
openai/gpt-4.1-nano -
Cohere: Command R+ (08-2024)
Modelscommand-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint...
cohere/command-r-plus-08-2024 -
API Client SDK taste
Prompts# API Client SDK taste of a developer-experience focused SDK maintainer - Generate the low-level client from an OpenAPI spec, and hand-write only a thin, idiomatic layer on top. Confidence: 0.85 - Treat the API spec as…
-
Tencent: Hy4 flash
ModelsHy4 flash is a cost-efficient variant of [Hy4](https://openrouter.ai/tencent/hy4) from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent...
tencent/hy4-flash -
gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...
openai/gpt-oss-safeguard-20b -
OpenAI: GPT-5 Nano (batch)
ModelsGPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...
openai/gpt-5-nano:batch
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.