$ loading_
Generate images, videos, and audio with one unified AI media workflow.
The skill appears largely prompt/documentation-oriented, but the README shows it actually depends on a fal.ai MCP service, requires an FAL_KEY, and supports file upload plus remote generation, so the overall posture is best rated as caution. Open-source status and strong community adoption are positive signals, but the stated “no key/no remote endpoint” conflicts with the README and the source mapping should be verified.
The README explicitly requires an FAL_KEY in the MCP configuration, so actual use involves an API credential. This is a normal third-party service pattern, but it conflicts with the metadata claiming “no key,” creating a caution around credential handling and documentation accuracy.
The materials show use of fal.ai MCP operations such as search, generate, result, and upload, including uploading images as inputs. This means prompts, media files, and generation requests are sent to fal.ai-related remote services. That is normal for this type of media-generation tool, with no extra unknown endpoints shown, but it conflicts with the metadata stating “no remote endpoint.”
The README instructs users to start the MCP service via `npx -y fal-ai-mcp-server`, which means a local Node/npm process is launched to provide the tool capability. This is a common MCP execution model and not high risk by itself, but it does involve local process execution and runtime dependencies.
The documentation shows `upload(file_path: "/path/to/image.png")`, indicating the tool can read user-specified local files and upload them remotely for generation/editing. The material does not show broad local data harvesting or excessive permissions, but there is a clear exfiltration surface for selected files.
Positive signals include a GitHub source, open-source status, and very strong community adoption, all of which materially lower risk. However, the provided repository link `affaan-m/ECC` does not obviously match the skill name or the fal.ai MCP described in the README, and the license is undeclared with unknown maintenance status, so there is still supply-chain uncertainty that should be verified.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "fal-ai-media" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/fal-ai-media/SKILL.md 2. Save it as ~/.claude/skills/fal-ai-media/SKILL.md 3. Reload skills and tell me it's ready
Use Nano Banana to generate a promotional poster image for a new coffee machine. Style: modern minimalist, warm lighting, premium kitchen setting, with space reserved for headline text.
A high-quality product poster image suitable for marketing use.
Create a 10-second branded video from this copy: 'The first cup in the morning awakens a day of inspiration.' Include coffee pouring into a cup, rising steam, and an ending brand logo shot with a premium visual style.
A branded short video ready for social media publishing.
Use CSM-1B to generate a Chinese female voiceover for this product intro in a warm, professional tone with natural pacing: 'This smartwatch supports all-day health monitoring, making every step more meaningful.'
A natural-sounding voiceover audio track ready for a product video.
Drift-prone skill. fal.ai model IDs, pricing, inputs, and MCP tool names change quickly. Search or fetch the current model metadata before promising a specific model, parameter, output format, or cost.
Generate images, videos, and audio using fal.ai models via MCP.
fal.ai MCP server must be configured. Add to ~/.claude.json:
"fal-ai": {
"command": "npx",
"args": ["-y", "fal-ai-mcp-server"],
"env": { "FAL_KEY": "YOUR_FAL_KEY_HERE" }
}
Get an API key at fal.ai.
The fal.ai MCP provides these tools:
search — Find available models by keywordfind — Get model details and parametersgenerate — Run a model with parametersresult — Check async generation statusstatus — Check job statuscancel — Cancel a running jobestimate_cost — Estimate generation costmodels — List popular modelsupload — Upload files for use as inputsBest for: quick iterations, drafts, text-to-image, image editing.
generate(
app_id: "fal-ai/nano-banana-2",
input_data: {
"prompt": "a futuristic cityscape at sunset, cyberpunk style",
"image_size": "landscape_16_9",
"num_images": 1,
"seed": 42
}
)
Best for: production images, realism, typography, detailed prompts.
generate(
app_id: "fal-ai/nano-banana-pro",
input_data: {
"prompt": "professional product photo of wireless headphones on marble surface, studio lighting",
"image_size": "square",
"num_images": 1,
"guidance_scale": 7.5
}
)
| Param | Type | Options | Notes |
|---|---|---|---|
prompt | string | required | Describe what you want |
image_size | string | square, portrait_4_3, landscape_16_9, portrait_16_9, landscape_4_3 | Aspect ratio |
num_images | number | 1-4 | How many to generate |
seed | number | any integer | Reproducibility |
guidance_scale | number | 1-20 | How closely to follow the prompt (higher = more literal) |
Use Nano Banana 2 with an input image for inpainting, outpainting, or style transfer:
# First upload the source image
upload(file_path: "/path/to/image.png")
# Then generate with image input
generate(
app_id: "fal-ai/nano-banana-2",
input_data: {
"prompt": "same scene but in watercolor style",
"image_url": "<uploaded_url>",
"image_size": "landscape_16_9"
}
)
Best for: text-to-video, image-to-video with high motion quality.
generate(
app_id: "fal-ai/seedance-1-0-pro",
input_data: {
"prompt": "a drone flyover of a mountain lake at golden hour, cinematic",
"duration": "5s",
"aspect_ratio": "16:9",
"seed": 42
}
)
Best for: text/image-to-video with native audio generation.
generate(
app_id: "fal-ai/kling-video/v3/pro",
input_data: {
"prompt": "ocean waves crashing on a rocky coast, dramatic clouds",
"duration": "5s",
"aspect_ratio": "16:9"
}
)
Best for: video with generated sound, high visual quality.
generate(
app_id: "fal-ai/veo-3",
input_data: {
"prompt": "a bustling Tokyo street market at night, neon signs, crowd noise",
"aspect_ratio": "16:9"
}
)
Start from an existing image:
generate(
app_id: "fal-ai/seedance-1-0-pro",
input_data: {
"prompt": "camera slowly zooms out, gentle wind moves the trees",
"image_url": "<uploaded_image_url>",
"duration": "5s"
}
)
…
Design Quarkus 3 backend patterns for messaging, APIs, data, and async workflows.
Use Bun for runtime, bundling, testing, packages, and Node migration decisions.
Use the correct Ethereum Keccak-256 hashing in Node.js and TypeScript.
Apply Nuxt 4 patterns for SSR safety, performance, and data fetching.
Handle returns, refunds, fraud checks, and warranty claim decisions efficiently.
Review Solidity AMM, liquidity pool, and swap flow security risks.
Generate and edit images, create videos, and handle media from URLs or disk.
Generate images, videos, and audio with 100+ AI models via muapi.ai.
Generate images from prompts fast with customizable ratio, count, and format.
Detect AI-generated signals in media and text to identify synthetic content.
Automatically split scenes, generate subtitles, and extract thumbnail data for videos.
Generate high-quality images, videos, and audio for AI-driven creative workflows.