Fal Models Catalog

fal-ai-community/skills/skills/fal-models-catalog

作者 fal-ai-community9ca850412943251fc9a466c4c29fdaf7a303a3d8无许可证250 个星标收录于 2026年10月9日更新于 2026年10月9日仓库10天前更新

Choose the right fal.ai endpoint for a given task. Modality-organized catalog of production endpoint defaults, text-to-image, image-to-image, text-to-video, image-to-video, and more. Use when the user has not named a specific model, or asks "which model for X", "best endpoint for Y", "what should I use for Z".

仅含说明AI & Agents
AI 生成的概览

该技能是一个目录,帮助为媒体生成或编辑任务选择合适的 fal.ai 端点。

功能
该技能是按模态组织的 fal.ai 生产端点目录,涵盖文本生成图像、图像生成图像、文本生成视频、图像生成视频、视频生成视频、文本生成 3D、图像生成 3D、文本生成音频、音频转文本和图像转文本。它把任务路由到对应的参考文件,文件中按用例(如高端写实、快速低成本、4K 或专用)列出精选端点。它还描述了使用 genmedia CLI 确认、查看和查询端点价格的验证流程,并指向另一个技能以获取工作流实用端点。
适用场景
当用户未指定具体模型,询问哪个模型或端点适合某项任务,或询问某项媒体生成或编辑工作该用什么时使用。它用于在调用 fal.ai 端点之前进行选择。
运行要求
需要 genmedia CLI 来调用端点,若未安装需先执行一次 genmedia init;该技能本身不包含脚本,只有参考文档。端点调用意味着需要访问 fal.ai 服务的网络连接。

fal.ai Models Catalog

Endpoint-first navigation for fal.ai production work. Each modality reference lists curated picks organized by use case (premium realism / fast & cheap / 4K / specialized). Before reaching for free-text search, consult the modality reference that matches the task.

Runtime: All endpoint calls run via the genmedia CLI. See the genmedia skill for command syntax; run genmedia init once if not yet installed.

Endpoint-first rule

  1. Pick the endpoint ID from the right modality reference.
  2. Verify it: genmedia models --endpoint_id <endpoint_id> --json.
  3. Inspect it: genmedia schema <endpoint_id> --json.
  4. Check cost when relevant: genmedia pricing <endpoint_id> --json.
  5. Use text search only if the routed endpoint is missing, deprecated, rejected, or the role is not covered here:
bash
genmedia models "<task description>" --jsongenmedia docs "<topic>" --json

Do not invent endpoint IDs.

Modality references

Load the reference matching the user's task:

  • text-to-image.md [blocked], image generation from prompt (text-heavy, premium still, fast draft)
  • image-to-image.md [blocked], image editing, inpainting, background removal, upscaling
  • text-to-video.md [blocked], video generation from prompt (highest quality, fast/economical, multi-shot storytelling)
  • image-to-video.md [blocked], video from a reference frame (including audio-driven and lip-sync variants)
  • video-to-video.md [blocked], video edit, restyle, upscale, background removal
  • text-to-3d.md [blocked], 3D model generation from text
  • image-to-3d.md [blocked], 3D model generation from reference images
  • text-to-audio.md [blocked]. TTS, music, SFX generation
  • audio-to-text.md [blocked], speech-to-text (Whisper, ElevenLabs Scribe with diarization)
  • image-to-text.md [blocked]. OCR, captioning, VQA, detection, segmentation

Utility endpoints

Workflow utility endpoint IDs (resize, composite, mask, audio merge, subtitle, etc.) live in the fal-workflow skill: fal-workflow/references/utility-endpoints.md.

Utility endpoints are explicit because they are deterministic tools, not creative model choices. Always inspect schema before use.

来源与署名

来源:fal-ai-community/skills位于skills/fal-models-catalog提交9ca8504

许可证: 无许可证

内容归原作者所有。SourceWeft 从公开仓库中收录这些内容。

举报或申请下架