利用Shopify公开的products.json以低成本（每个视频约$0.12）生成产品视频，并使用原始产品图片作为锚定帧，避免AI生成幻觉。
Before: ordinary catalog photos, pulled straight from deathwishcoffee.com's public products.json.
↓ gen4.5 image → video ↓
After: a Reels-ready 9:16 video per product, the catalog photo preserved as the anchor frame. Full-quality MP4s in examples/.
Point it at a store. It pulls each product's photo, animates it with gen4.5 (your catalog shot is the anchor frame, so the product stays true, no hallucinated variants), and exports a Reels-ready 9:16 video per product.
Your first run: about ten minutes. A 5-second clip is 60 credits (~$0.60), so the $10 minimum credit purchase covers around 16 product videos.
git clone https://github.com/fabriciocarraro/runway-shopify-pipeline && cd runway-shopify-pipeline
pip install -r requirements.txt
cp .env.example .env # add your API key → get one at https://dev.runwayml.com
python catalog_to_video.py --catalog sample_catalog.json --dry-run # sanity check: runs with no key, spends nothing
python catalog_to_video.py --store yourstore.myshopify.com --skus 5 # the real thing: YOUR products, moving
That second command is the whole point: most Shopify stores expose products.json publicly, so this runs against your real catalog with zero app installs and zero auth dances.
What a run looks like:
🛍 Fetching catalog from yourstore.myshopify.com …
3 of 3 products to generate · 5s each · est. ~180 credits (~$1.80)
🚀 submitted retro-runner-sneaker (task 21dcba8c…)
🚀 submitted soy-candle-cedar (task 0a4214c4…)
🚀 submitted steel-bottle-750ml (task 9f9086d4…)
✅ retro-runner-sneaker.mp4
✅ soy-candle-cedar.mp4
✅ steel-bottle-750ml.mp4
🎬 3 videos · 6m42s wall-clock · ~180 credits (~$1.80)
📣 Tweet-ready: "I turned yourstore.myshopify.com's catalog into 3 product videos in 6 minutes, for about $1.80. No shoot, no agency. One script."
Tip:
--dry-runpreviews any run, live store included, without spending a credit. To ge
Turn any Shopify catalog into product videos with the Runway API. One script, gen4.5 image-to-video.
根据分类、Topic 和编程语言匹配的相似项目。
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.