skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
fal-ai-community/skills83 installs

fal-train

Train custom AI models (LoRA) on fal.ai — personalize image generation for specific people, styles, objects, or video generation. Use when the user requests "Train model", "Train LoRA", "Fine-tune", "Custom model", "Train on my images", "Portrait training".

How do I install this agent skill?

npx skills add https://github.com/fal-ai-community/skills --skill fal-train
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill provides a shell script to interact with the fal.ai API for training custom AI models (LoRAs). It uses standard tools like curl and jq to manage API requests and follows best practices for credential management by using environment variable files.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · 1 issue

  • Runlayerpass

    2/2 files flagged

  • ZeroLeakspass

    Score: 93/100 · 2 sections analyzed

What does this agent skill do?

fal-train

Train custom LoRA models on fal.ai for personalized AI generation.

Scripts

ScriptPurpose
train.shSubmit a LoRA training job

Usage

Train Image LoRA (Style/Subject/Person)

./scripts/train.sh --images-url "https://example.com/training-images.zip" --trigger-word "sks style" --model fal-ai/flux-lora-fast-training

Train Portrait LoRA

./scripts/train.sh --images-url "https://example.com/face-photos.zip" --trigger-word "ohwx person" --model fal-ai/flux-lora-portrait-trainer

Check Training Status

./scripts/train.sh --status --endpoint fal-ai/flux-lora-fast-training --request-id "abc123"

Arguments

ArgumentDescriptionRequired
--images-urlURL to zip of training imagesYes
--trigger-wordWord to activate the LoRA in promptsYes
--model / -mTraining model endpointNo (default: fal-ai/flux-lora-fast-training)
--stepsTraining stepsNo (default: 1000)
--statusCheck training job statusNo
--endpointEndpoint for status checkWith --status
--request-idRequest ID for status checkWith --status
--paramExtra param as key=value (repeatable)No

Finding Models

To discover the best and latest training/LoRA models, use the search API:

# Search for LoRA training models
bash /mnt/skills/user/fal-generate/scripts/search-models.sh --query "lora training"
bash /mnt/skills/user/fal-generate/scripts/search-models.sh --query "trainer"
bash /mnt/skills/user/fal-generate/scripts/search-models.sh --query "fine-tune"

Or use the search_models MCP tool with keywords like "lora", "training", "trainer", "fine-tune".

Training Data Tips

  • People: 10-20 photos, varied angles/lighting/expressions, consistent person
  • Styles: 10-15 images exemplifying the style, diverse subjects
  • Objects: 5-15 photos from different angles on various backgrounds
  • Images should be high quality, at least 512x512
  • Zip all images into a single .zip file and host at a URL

Output Format

{
  "diffusers_lora_file": {
    "url": "https://fal.media/files/.../lora.safetensors",
    "content_type": "application/octet-stream",
    "file_name": "lora.safetensors",
    "file_size": 12345678
  },
  "config_file": {
    "url": "https://fal.media/files/.../config.json"
  }
}

Use the diffusers_lora_file.url as the lora_url parameter when generating images with FLUX models.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/fal-ai-community/skills/fal-train">View fal-train on skillZs</a>