What makes Fannabe Generate notable?

969 downloads. Trust evidence available

How should Fannabe Generate be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Fannabe Generate

Generate images, videos, and voice for your AI models via Fannabe. Use when: "generate an image", "make a video of my model", "animate this photo", "image-to... Skill: Fannabe Generate Owner: fannabe Summary: Generate images, videos, and voice for your AI models via Fannabe. Use when: "generate an image", "make a video of my model", "animate this photo", "image-to... Tags: latest:0.1.5 Version history: v0.1.5 | 2026-07-09T10:56:55.605Z | user Renamed --character flag to --model (matches the CLI/MCP's persona=model, engine=ai terminology). Added a 'Concepts: model vs AI' glos

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

969

Updated

Oct 12, 2026

Version

0.1.5

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 969 downloads reported by the source. Last updated 10/12/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 969 downloadsadoption · observed Oct 12, 2026
Latest release: 0.1.5release · observed Jul 9, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 0.1.5release
Renamed --character flag to --model (matches the CLI/MCP's persona=model, engine=ai terminology). Added a 'Concepts: model vs AI' glossary to SKILL.md. No functional changes.
Observed Jul 9, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s17bdvp9nk4b7jb6sgmnd9w3td8a24jq:fannabe-generate

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-fannabe-fannabe-generate/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

81,090 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
version: 0.1.5
name: fannabe-generate
description: |
  Generate images, videos, and voice for your AI models via Fannabe.
  Use when: "generate an image", "make a video of my model",
  "animate this photo", "image-to-video", "motion control / transfer this
  dance onto my model", "character swap", "edit/restyle this image",
  "caption this video", "improve/rewrite this prompt", "describe this photo
  as a prompt", "show my gallery", "download my latest render", or
  "how many credits do I have". Wraps the `fannabe` CLI, which runs the same
  AI engines, settings, and credit pricing as the Fannabe web studio.
  NOT for: training new models (done in the web studio), or non-Fannabe
  providers.
argument-hint: "[what-to-generate] [--model <name-or-id>] [--ai <id>]"
homepage: https://www.fannabe.com
allowed-tools: Bash
metadata:
  {
    "openclaw":
      {
        "requires": { "bins": ["node"] }
      }
  }
---

# Fannabe Generate

Create AI-model images, videos, and voice from the terminal. This skill drives the `fannabe` CLI, which talks to the Fannabe API and spends the signed-in user's credits.

## Step 0 — Bootstrap (before anything else)

1. If `fannabe` is not on `$PATH`, install it:
   ```bash
   npm install -g @fannabe/cli
   ```
2. If a command fails with a "Not logged in" / 401 error, ask the user to run `fannabe auth login` (opens a browser) and wait for confirmation. The token is cached in `~/.fannabe`.

Every command supports `--help`, and output is plain text meant to be parsed.

## Concepts: model vs. AI

Two different things are both called "model" colloquially:

- **Model** (`fannabe models`, `--model <modelId>`): the user's own AI persona — who the content is of.
- **AI** (`fannabe ai`, an `<aiId>` like `nano-banana-2-single-image`): the generation engine that renders it — what renders it.

Every `generate create` call takes both.

## Core workflow

```bash
fannabe models list                           # pick a model (id, name, appearance)
fannabe ai list --media-type image            # pick an AI (first column is the id)
fannabe ai schema <aiId>                       # discover that AI's fields + source slots
fannabe generate create <aiId> \
  --model <modelId> --media-type image \
  --prompt "golden hour rooftop portrait, cinematic" \
  --set aspectRatio=9:16 --set resolution=1k \
  --wait --download ./output                  # prints cost, blocks until done, saves the file
```

- Match the user's wording to a model with `fannabe models list --search "<text>"` (matches name and appearance, e.g. "redhead").
- Set any AI field with repeatable `--set key=value` (see `ai schema <aiId>`), or a full `--settings '<json>'`.
- Preview spend first with `fannabe generate cost <aiId> --media-type image --model <modelId> --set resolution=1k`.

## When the user describes an outfit or scene in plain words

Prefer the curated Theme/Outfit presets over a long hand-written prompt. See [references/easy-mode.md](references/easy-mode.md).

## Ima

_meta.json

{
  "ownerId": "kn77p1ycdwdfkpw3bs6nn8yr718a3gpf",
  "slug": "fannabe-generate",
  "version": "0.1.5",
  "publishedAt": 1783594615605
}

references/ai.md

# Choosing an AI

List AI engines per media type, then read the chosen AI's schema before generating.

```bash
fannabe ai list --media-type image      # image | video | audio | lip-sync
fannabe ai schema <aiId>                # exact fields, defaults, and source slots
```

- The first column of `ai list` is the AI id you pass to `generate create`.
- AI ids are a stable public contract (e.g. `nano-banana-2-single-image`, `kling-2-6-motion-control`); prefer them over guessing.
- `ai schema <aiId> --concept-type <type>` shows fields for a specific concept (e.g. `single-image`, `carousel`, `video-from-image`, `talking-video`). `--simple` shows the simple-mode fields.
- `economyMode` (a `--set economyMode=true` flag on supported AI) trades priority for a lower price.

Pass `--concept-type <type>` on `generate create` so the request runs the intended concept rather than a generic default.

references/easy-mode.md

# Easy mode: Theme and Outfit presets

When the user describes a location or outfit in plain words (a cafe, goth clothes, the gym, the beach), prefer the curated presets over a long hand-written prompt. They are platform-tuned and generally produce better results.

```bash
fannabe ai options --filter topic  --media-type image   # Themes (e.g. mirror-selfie, dubai)
fannabe ai options --filter outfit --media-type image   # Outfits (e.g. casual, gym)

fannabe generate create <aiId> \
  --model <modelId> --media-type image --concept-type single-image \
  --set locationPrompt=<themeId> --set outfitPrompt=<outfitId> \
  --set aspectRatio=9:16 --set resolution=1k \
  --wait --download ./output
```

Using a `locationPrompt` or `outfitPrompt` automatically switches the request to simple mode so the preset actually applies. The ids come from the `ai options` listing.

references/prompt-tools.md

# Prompt assistance

The same assist features as the studio's prompt box, usable standalone or inline on a generation.

## Standalone

```bash
fannabe prompt improve "girl on a beach" --media-type image --workflow <aiId>
fannabe prompt ai-edit "make it nighttime" --prompt "girl on a beach" --media-type image
fannabe prompt from-image ./inspo.jpg                  # describe a photo as a prompt
fannabe prompt tools list                              # JSON Prompt Generator, Video Prompter, ...
fannabe prompt tools run <toolId> "a beach scene"
```

## Inline on `generate create`

- `--enhance-prompt` — LLM rewrite/expansion pass (expert mode)
- `--from-image <path-or-url>` — derive the prompt from a photo via vision
- `--ai-edit "<instruction>"` — rewrite the current prompt per an instruction

They compose in that order: from-image, then prompt, then ai-edit.

Github ReposUpdated 4d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular