# AI Art Prompt & Model Trend Tracker (`dsh-org/ai-art-prompt-model-trend-tracker`) Actor Track trending AI art models, LoRAs, and prompt engineering techniques from Civitai. Get generation parameters, trigger words, and style recipes behind popular images. SFW-only by default. Snapshot or monitor mode for new-trend alerts. - **URL**: https://apify.com/dsh-org/ai-art-prompt-model-trend-tracker.md - **Developed by:** [DSH](https://apify.com/dsh-org) (community) - **Categories:** AI, Developer tools, Other - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $3.00 / 1,000 symbol trackeds This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Civitai Model & Prompt Trend Tracker Track **trending AI models, LoRAs, and prompts** on **Civitai** — the actual **prompts**, **trigger words**, and **generation parameters** behind what's rising this week in AI art. This is **prompt-engineering intelligence**, not a catalog dump: instead of "list every model," it answers *"what's working in AI image generation right now."* Built on Civitai's **official REST API**, no browser, **SFW-only by default**. Perfect for **prompt engineers**, **AI art creators**, and **AI tool builders** who want trending **Stable Diffusion / SDXL / Flux / Pony** models and the prompt patterns driving the most popular images. ### What you get Two result types in one dataset, each row tagged with `resultType` (`"model"` or `"prompt"`) so you can split them downstream. #### Trending model fields | Field | Description | |---|---| | `id`, `name`, `type` | Civitai model ID, name, and type (Checkpoint, LORA, TextualInversion, …) | | `baseModel` | Base model of the latest version (e.g. `SDXL 1.0`, `Flux.1 D`, `Pony`) | | `creator` | Uploader username | | `tags` | Model tags | | `triggerWords` | Trigger / trained words — the key tokens to activate the model | | `stats` | `downloads`, `thumbsUp`, `thumbsDown`, `comments` | | `trendPeriod`, `trendRank` | Trend window and rank (1 = top) | | `publishedAt`, `latestVersionName`, `latestVersionId` | Version metadata | | `sampleImageUrls` | Up to 3 SFW sample image URLs | | `modelUrl` | Direct Civitai link | | `isNew` | `true` if new to trending since the last monitor run (`null` in snapshot mode) | | `scrapedAt` | ISO 8601 timestamp | #### Trending prompt fields | Field | Description | |---|---| | `imageId`, `imageUrl` | Civitai image ID and direct URL | | `prompt`, `negativePrompt` | The actual generation prompt and negative prompt | | `generationParams` | `steps`, `sampler`, `cfgScale`, `seed`, `size` | | `model` | Checkpoint used: `{ name, type, versionId }` | | `loras` | LoRAs used: `[{ name, weight, versionId }]` | | `baseModel` | Base model where available | | `reactions` | Total reactions (like + heart + laugh + cry) | | `creator`, `tags` | Uploader and tags | | `trendPeriod`, `trendRank`, `isNew`, `scrapedAt` | Trend + monitor metadata | ### Two data types — which to use - **Trending models** (`dataType: "models"`) — what models and LoRAs are rising. Use it to track model adoption, discover emerging LoRAs, and grab trigger words for your prompts. - **Trending prompts** (`dataType: "prompts"`) — the prompts and generation settings behind the most popular images. Use it to see what prompt structures, style modifiers, samplers, and CFG values are actually working right now. - **Both** (`dataType: "both"`, the default) — run both in one pass. ### Monitor mode — track new trends over time Set `mode: "monitor"` and schedule the actor (daily or weekly): - **First run** stores the current trending IDs and returns everything. - **Later runs** return **only entries new to the trending list** since the previous run, each flagged `isNew: true`. - If nothing new is trending, the run finishes cleanly with an empty dataset (not an error). State is keyed per data type and trend period (`state-models-Week`, `state-prompts-Day`, …) and persisted in a named Key-Value Store, so it survives across scheduled runs. This is the "alert me when something new starts trending" workflow. ### SFW filtering (default) Civitai hosts a large amount of NSFW content. **This actor returns SFW content only by default.** It applies Civitai's server-side SFW request filter *and* a client-side safety check on every result and sample image. To include NSFW-tagged content, set `includeNsfw: true` — but the **default output is always SFW**. ### Input examples **Zero-config** — this week's trending SFW models and prompts: ```json {} ```` **Trending LoRAs for Flux, daily window:** ```json { "dataType": "models", "modelTypes": ["LORA"], "baseModels": ["Flux.1 D"], "trendPeriod": "Day", "sortModels": "Most Downloaded", "limit": 50 } ``` **Monitor new trending prompts every day:** ```json { "dataType": "prompts", "mode": "monitor", "trendPeriod": "Day", "sortPrompts": "Most Reactions", "limit": 100 } ``` ### Output examples **Trending model:** ```json { "resultType": "model", "id": 257749, "name": "Photorealistic Portrait XL", "type": "Checkpoint", "baseModel": "SDXL 1.0", "creator": "studio_example", "tags": ["photorealistic", "portrait", "base model"], "triggerWords": ["ppxl style"], "stats": { "downloads": 184320, "thumbsUp": 9421, "thumbsDown": 53, "comments": 412 }, "trendPeriod": "Week", "trendRank": 1, "publishedAt": "2026-05-30T09:12:00.000Z", "latestVersionName": "v3.0", "latestVersionId": 318204, "sampleImageUrls": ["https://image.civitai.com/.../a1.jpeg"], "modelUrl": "https://civitai.com/models/257749", "isNew": null, "scrapedAt": "2026-06-19T10:00:00.000Z" } ``` **Trending prompt:** ```json { "resultType": "prompt", "imageId": 49281756, "imageUrl": "https://image.civitai.com/.../p1.jpeg", "prompt": "a serene mountain lake at dawn, soft volumetric light, ultra detailed, 8k", "negativePrompt": "blurry, lowres, watermark", "generationParams": { "steps": 30, "sampler": "DPM++ 2M Karras", "cfgScale": 7, "seed": 1234567890, "size": "832x1216" }, "model": { "name": "Photorealistic Portrait XL", "type": "checkpoint", "versionId": 318204 }, "loras": [{ "name": "Film Grain XL", "weight": 0.8, "versionId": 305112 }], "baseModel": "SDXL 1.0", "reactions": 1542, "creator": "creator_example", "tags": ["landscape", "photorealistic"], "trendPeriod": "Week", "trendRank": 1, "isNew": null, "scrapedAt": "2026-06-19T10:00:00.000Z" } ``` ### Use cases - **Prompt engineers** staying on top of what's working in AI image generation — trending prompts, samplers, CFG values, and trigger words. - **Content creators** finding trending styles and techniques to ride the wave. - **AI tool builders** tracking model adoption and emerging LoRAs. - **Researchers** monitoring the AI art ecosystem and how prompt patterns shift week to week. - **Marketing & creative teams** tracking visual trends for creative direction. Pairs well with prompt-engineering tools like [Suvio](https://suvio.io) for turning trending prompts into production-ready workflows. ### Limitations - **Civitai API rate limits.** The actor throttles requests and retries on HTTP 429 with backoff. Increase `requestDelayMs` if you hit limits. - **Image metadata isn't always present.** Many Civitai images have no generation metadata; those are skipped for prompt extraction (no prompt = no value), so a large `limit` may page through several requests. - **SFW filter coverage.** SFW filtering relies on Civitai's content flags plus a client-side check. It is reliable for mainstream use but not a guarantee against mislabeled content. - **Trend windows.** `trendPeriod` is bounded to Day / Week / Month, matching Civitai's API. ### Pricing (Pay-Per-Event) You pay only for what you pull: | Event | When | |---|---| | `run-start` | Once per run | | `models-tracked` | Per trending model returned | | `prompts-extracted` | Per trending prompt returned | In **monitor mode**, only **new** trending entries are charged — checking state is free. Exact prices are shown on the actor's pricing tab. ### FAQ **Do I need a Civitai API key?** No — public trending data works without one. An optional `civitaiApiToken` field is available if you have one or if an endpoint requires it. **Can I schedule it?** Yes. Use monitor mode with an Apify Schedule (daily/weekly) to get only newly trending entries each run. **Can I filter by base model or type?** Yes — `baseModels` (e.g. `SDXL 1.0`, `Flux.1 D`, `Pony`) and `modelTypes` (e.g. `LORA`, `Checkpoint`) for the models data type, plus an optional `tag`. **Is NSFW content included?** No, not by default. Output is SFW-only unless you explicitly set `includeNsfw: true`. **Roadmap.** A Lexica-based prompt-trend source is documented as a future fallback/addition for even cleaner, search-curated prompt data. # Actor input Schema ## `dataType` (type: `string`): What to pull. models = trending models & LoRAs. prompts = trending prompts (with generation parameters) from popular images. both = run both in one run. ## `mode` (type: `string`): snapshot = return the current trending results (no state). monitor = on the first run store the trending IDs, then on later runs output ONLY entries that are NEW to the trending list since the previous run (ideal for scheduled daily/weekly alerts). ## `trendPeriod` (type: `string`): Time window used to rank trending results. ## `limit` (type: `integer`): Maximum number of results per data type (models and prompts counted separately). Civitai caps a single page at 100 models / 200 images; higher limits are paged via cursors. ## `modelTypes` (type: `array`): Restrict trending models to these Civitai model types. Leave empty for all types. (Only applies to the 'models' data type.) ## `baseModels` (type: `array`): Restrict trending models to these base models, e.g. "SDXL 1.0", "Flux.1 D", "Pony", "SD 1.5". Leave empty for all. (Only applies to the 'models' data type.) ## `sortModels` (type: `string`): Ranking used for the 'models' data type. ## `sortPrompts` (type: `string`): Ranking used for the 'prompts' data type (based on the Civitai images endpoint). ## `tag` (type: `string`): Optional tag to filter trending models by (e.g. "anime", "photorealistic", "style"). ## `includeGenerationParams` (type: `boolean`): Include steps, sampler, CFG scale, seed and size in each trending prompt result. Turn off for a leaner prompt-text-only output. ## `includeNsfw` (type: `boolean`): OFF by default — results are filtered to SFW only (server-side request filter plus a client-side safety check). Turn ON to include NSFW-tagged models and images. Default output is always SFW. ## `civitaiApiToken` (type: `string`): Optional. Civitai public read endpoints generally work without a token, but some endpoints/accounts may require one. Create a token at civitai.com/user/account. Stored securely. ## `requestDelayMs` (type: `integer`): Throttle between Civitai API requests to respect rate limits. Increase if you see HTTP 429 responses. ## Actor input object example ```json { "dataType": "both", "mode": "snapshot", "trendPeriod": "Week", "limit": 100, "modelTypes": [], "baseModels": [], "sortModels": "Most Downloaded", "sortPrompts": "Most Reactions", "includeGenerationParams": true, "includeNsfw": false, "requestDelayMs": 500 } ``` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = {}; // Run the Actor and wait for it to finish const run = await client.actor("dsh-org/ai-art-prompt-model-trend-tracker").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = {} # Run the Actor and wait for it to finish run = client.actor("dsh-org/ai-art-prompt-model-trend-tracker").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{}' | apify call dsh-org/ai-art-prompt-model-trend-tracker --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=dsh-org/ai-art-prompt-model-trend-tracker", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "AI Art Prompt & Model Trend Tracker", "description": "Track trending AI art models, LoRAs, and prompt engineering techniques from Civitai. Get generation parameters, trigger words, and style recipes behind popular images. SFW-only by default. Snapshot or monitor mode for new-trend alerts.", "version": "0.0", "x-build-id": "VPdf5GKh38hQXlaNa" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dsh-org~ai-art-prompt-model-trend-tracker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dsh-org-ai-art-prompt-model-trend-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dsh-org~ai-art-prompt-model-trend-tracker/runs": { "post": { "operationId": "runs-sync-dsh-org-ai-art-prompt-model-trend-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dsh-org~ai-art-prompt-model-trend-tracker/run-sync": { "post": { "operationId": "run-sync-dsh-org-ai-art-prompt-model-trend-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "dataType": { "title": "Data type", "enum": [ "models", "prompts", "both" ], "type": "string", "description": "What to pull. models = trending models & LoRAs. prompts = trending prompts (with generation parameters) from popular images. both = run both in one run.", "default": "both" }, "mode": { "title": "Mode", "enum": [ "snapshot", "monitor" ], "type": "string", "description": "snapshot = return the current trending results (no state). monitor = on the first run store the trending IDs, then on later runs output ONLY entries that are NEW to the trending list since the previous run (ideal for scheduled daily/weekly alerts).", "default": "snapshot" }, "trendPeriod": { "title": "Trend period", "enum": [ "Day", "Week", "Month" ], "type": "string", "description": "Time window used to rank trending results.", "default": "Week" }, "limit": { "title": "Limit per data type", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum number of results per data type (models and prompts counted separately). Civitai caps a single page at 100 models / 200 images; higher limits are paged via cursors.", "default": 100 }, "modelTypes": { "title": "Model types filter", "type": "array", "description": "Restrict trending models to these Civitai model types. Leave empty for all types. (Only applies to the 'models' data type.)", "items": { "type": "string", "enum": [ "Checkpoint", "LORA", "LoCon", "TextualInversion", "Hypernetwork", "AestheticGradient", "Controlnet", "Upscaler", "MotionModule", "VAE", "Poses", "Wildcards", "Workflows", "Other" ] }, "default": [] }, "baseModels": { "title": "Base models filter", "type": "array", "description": "Restrict trending models to these base models, e.g. \"SDXL 1.0\", \"Flux.1 D\", \"Pony\", \"SD 1.5\". Leave empty for all. (Only applies to the 'models' data type.)", "default": [], "items": { "type": "string" } }, "sortModels": { "title": "Sort models by", "enum": [ "Most Downloaded", "Highest Rated", "Newest" ], "type": "string", "description": "Ranking used for the 'models' data type.", "default": "Most Downloaded" }, "sortPrompts": { "title": "Sort prompts by", "enum": [ "Most Reactions", "Most Comments", "Newest" ], "type": "string", "description": "Ranking used for the 'prompts' data type (based on the Civitai images endpoint).", "default": "Most Reactions" }, "tag": { "title": "Tag filter (optional)", "type": "string", "description": "Optional tag to filter trending models by (e.g. \"anime\", \"photorealistic\", \"style\")." }, "includeGenerationParams": { "title": "Include generation parameters", "type": "boolean", "description": "Include steps, sampler, CFG scale, seed and size in each trending prompt result. Turn off for a leaner prompt-text-only output.", "default": true }, "includeNsfw": { "title": "Include NSFW content", "type": "boolean", "description": "OFF by default — results are filtered to SFW only (server-side request filter plus a client-side safety check). Turn ON to include NSFW-tagged models and images. Default output is always SFW.", "default": false }, "civitaiApiToken": { "title": "Civitai API token (optional)", "type": "string", "description": "Optional. Civitai public read endpoints generally work without a token, but some endpoints/accounts may require one. Create a token at civitai.com/user/account. Stored securely." }, "requestDelayMs": { "title": "Delay between API requests (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Throttle between Civitai API requests to respect rate limits. Increase if you see HTTP 429 responses.", "default": 500 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```