Name: cohub-generate
Author: Neta

Skills Leaderboard

#Skill14 daysUses24h

Platform Published by the Neta team.

Official Made by the Neta team.

Verified Reviewed by the Neta team.

Community Shared by a Cohub user. Not reviewed — read SKILL.md before you use it.

cohub-generate

PlatformBuilt-incohub/cohub-generate

Use it in Cohub

Paste this into your agent's chat — it fetches the skill and follows it.

Use the skill: cohub-generate. Run `npx -y @neta-art/neta-search-cli@latest skills use cohub/cohub-generate --via site` and follow what it prints. Read its complete output, redirecting it to a temporary file first if necessary, and resolve relative paths from the skill directory it prints.

Install from a terminal

npx -y @neta-art/neta-search-cli@latest skills use cohub/cohub-generate

Summary

Generate images, videos, music, and speech from your world's material and text prompts.

Create images from descriptions, animate still pictures into video, or restyle existing images with new directions.
Generate background music or synthesize speech in designed or cloned voices from reference audio.
Works from text prompts alone, or combine prompts with reference images, video, or audio from your world.
Results appear as viewable links; download files when you need to edit or publish them locally.
Best with clear, concrete prompts: specific scenes, moods, or actions rather than abstract concepts.

SKILL.md

# Cohub Multimodal Generation

Use `cohub generate` to create or transform images, video, and music.

Prefer simple, explicit commands. Use `--json` when reading output for decisions, extracting URLs, or chaining commands. If a target Space is required, add `-s "$COHUB_SPACE_ID"` or an explicit Space ID.

## Installation

If `cohub` is unavailable, install it and check availability:

```bash
npm install -g @neta-art/cohub-cli
cohub --help
```

## Models

Always resolve models from the live list; do not hardcode a catalog.

```bash
cohub models ls --model-type multimodal --json
```

Typical categories: text-to-image / image editing, text-to-video / image-to-video, text-to-speech (TTS), background removal, music.

Before using non-default parameters or reference media, inspect the model schema for supported inputs, roles, parameters, defaults, and examples:

```bash
cohub models show <model> --json
```

## Generate

Default to returning generated result links directly, with Markdown preview when possible (`![alt](url)` for images, direct links for video and audio). Save locally only when the user asks for a file download, local editing, or post-processing.

Generate from text:

```bash
cohub generate "a calm lake at sunrise" \
  --model <model>
```

Generate with reference media:

```bash
cohub generate "restyle this image" \
  --model <model> \
  --image ./input.png
```

Supported inputs: `--image`, `--video`, and `--audio`, each accepting a local path or URL and repeatable.

When a model requires input roles, prefix the path or URL:

```bash
cohub generate "smooth transition between two shots" \
  --model <model> \
  --image first_frame=https://example.com/first.png \
  --image last_frame=https://example.com/last.png

cohub generate "keep these characters consistent" \
  --model <model> \
  --image reference_image=https://example.com/a.png \
  --image reference_image=https://example.com/b.png
```

Roles include `first_frame`, `last_frame`, `reference_image`, and `reference_video`. Check `models show` for what a model accepts.

Pass generation parameters with `--param key=value` (repeatable; JSON, number, or boolean values) or `--parameters '<json>'`:

```bash
cohub generate "cinematic drone shot over misty mountains" \
  --model <model> \
  --param duration=5 \
  --param resolution=720p \
  --param aspect_ratio=16:9
```

Other useful flags:

```bash
cohub generate "..." --model <model> --output ./out.png   # save locally
cohub generate "..." --model <model> --async              # queue and return
cohub generate "..." --model <model> --timeout-ms 120000  # sync wait limit
cohub generate "..." --model <model> --meta '<json>'      # attach metadata
```

## Speech (TTS)

The prompt is the text to speak. Design a voice with `qwen-audio-3.0-tts-plus` (no reference needed), or clone a voice with `higgs-tts` from reference audio.

Design a voice and speak:

```bash
cohub generate "This is a text-to-speech test. It should sound natural and clear." \
  --model qwen-audio-3.0-tts-plus \
  --meta '{"voice_prompt": "A calm, steady male narrator voice, clear and natural."}'
```

Clone that voice with reference audio (e.g. from a prior generation):

```bash
cohub generate "This is a voice clone test. It should sound like the reference." \
  --model higgs-tts \
  --audio <audio-url-or-path>
```

## Workflows

Animate a still image:

```bash
cohub generate "<motion prompt>" \
  --model <model> \
  --image first_frame=./still.png
```

Edit or restyle with a reference image:

```bash
cohub generate "<edit instruction>" \
  --model <model> \
  --image ./input.png
```

For less common options, use `cohub generate -h`.