Creating consistent character videos with Veo 3.1, GPT-4o, and Google NanoBanana
UnknownWhat this workflow does
This AI workflow has 31 nodes and runs on a schedule (every 6 hours). Along the way it connects OpenAI Chat Model, Telegram and Blotato (community). It also calls api.kie.ai over HTTP.
How it runs
Trigger: On a schedule (every 6 hours).
- Code: runs custom JavaScript code
- Story Creator Agent (Basic LLM Chain): sends a prompt to an LLM, with model: OpenAI Chat Model
- Code: runs custom JavaScript code
- Create Start Frame (HTTP Request): calls api.kie.ai (POST)
- Wait: waits 5 seconds
- Get Start Frame (HTTP Request): calls api.kie.ai
- Switch: routes items into 5 branches
- Start Frame Image Url (Code): runs custom JavaScript code
- Get Start Frame Binary (HTTP Request): calls an HTTP API
- Create End Frame (HTTP Request): calls api.kie.ai (POST)
…plus 17 more steps. See the full node list below.
Services it uses
HTTP calls to: api.kie.ai
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that @blotato/n8n-nodes-blotato is verified or supports 3.0 (used in Instagram, Tiktok1).
Nodes used (10)
- Code
n8n-nodes-base.code - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Blotato
@blotato/n8n-nodes-blotato.blotato - HTTP Request
n8n-nodes-base.httpRequest - Wait
n8n-nodes-base.wait - Switch
n8n-nodes-base.switch - Telegram
n8n-nodes-base.telegram
From the author
This n8n template demonstrates how to create consistent character videos using AI image and video generation. The workflow generates photorealistic videos featuring the same character across different poses, locations, and outfits, maintaining perfect…