From runway-pack
Generates text-to-video content via RunwayML Python client: select models like gen4_turbo, engineer prompts, batch process, output in ratios like 16:9 or 9:16.
npx claudepluginhub jeremylongshore/claude-code-plugins-plus-skills --plugin runway-packThis skill is limited to using the following tools:
Advanced text-to-video generation: prompt engineering, model selection, parameter tuning, and batch generation.
Generates text-to-video clips using Runway Gen-3 Alpha via Python SDK. Polls tasks, handles errors, downloads output. For AI video workflows.
Generates videos from text, images, or videos using Runway API models like seedance2, gen4.5, veo3 via Python scripts run with uv. Useful for AI video prototyping in code workflows.
Guides Next.js Cache Components and Partial Prerendering (PPR): 'use cache' directives, cacheLife(), cacheTag(), revalidateTag() for caching, invalidation, static/dynamic optimization. Auto-activates on cacheComponents: true.
Share bugs, ideas, or general feedback.
Advanced text-to-video generation: prompt engineering, model selection, parameter tuning, and batch generation.
runway-hello-worldfrom runwayml import RunwayML
client = RunwayML()
# Available models:
# gen3a_turbo — Fast, lower cost, good quality
# gen4_turbo — Latest model, highest quality
task = client.image_to_video.create(
model='gen4_turbo',
prompt_text='A futuristic cityscape at night with flying cars and neon signs, cyberpunk aesthetic',
duration=10,
ratio='16:9',
)
result = task.wait_for_task_output()
# Structure: Subject + Action + Setting + Style + Camera
prompts = [
# Good: specific, visual, stylistic
"A red fox walking through a snowy forest, soft winter light, documentary style, tracking shot",
# Good: detailed motion and camera
"Waves of golden wheat swaying in the wind, drone flyover, warm sunset, cinematic grain",
# Bad: too abstract
# "Something beautiful happening" — too vague
]
import asyncio
prompts = [
"A butterfly emerging from a cocoon, macro lens, time-lapse, studio lighting",
"Rain falling on a Tokyo street at night, reflections, neon, dolly zoom",
"A chef preparing sushi in a traditional kitchen, close-up, warm lighting",
]
tasks = []
for prompt in prompts:
task = client.image_to_video.create(
model='gen3a_turbo',
prompt_text=prompt,
duration=5,
)
tasks.append(task)
print(f"Queued: {task.id}")
# Wait for all
for task in tasks:
result = task.wait_for_task_output()
status = "OK" if result.status == "SUCCEEDED" else "FAILED"
print(f" {task.id}: {status}")
task = client.image_to_video.create(
model='gen3a_turbo',
prompt_text='Abstract paint mixing in slow motion, vibrant colors, black background',
duration=5,
ratio='9:16', # Vertical for mobile/TikTok
# ratio='16:9', # Landscape for YouTube
# ratio='1:1', # Square for Instagram
)
| Issue | Cause | Solution |
|---|---|---|
| Low quality | Gen3a_turbo for complex scene | Use gen4_turbo for higher quality |
| Content rejection | Policy violation | Remove violent/explicit content from prompt |
| Slow generation | High queue | Use turbo model or try later |
| Wrong aspect ratio | Not specified | Always set ratio explicitly |
Image-to-video: runway-core-workflow-b