Generate and quality control images with DALL-E 2 and human review loop
UnknownUnknown. This template uses community nodes we can't verify statically. Uses community nodes that can't be verified statically (unverified community packages are off by default in 3.0). Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 8 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenAI and Gotohuman (community).
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Set Image Prompt (Edit Fields (Set)): sets 2 fields: Prompt, Name
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Initial Image Generation (OpenAI): work with image
- Initial Review (Goto Human): uses Goto Human
- If: checks a condition and branches into true / false
- Second Image Generation (OpenAI): work with image
- Second Review (Goto Human): uses Goto Human
Services it uses
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 @gotohuman/n8n-nodes-gotohuman is verified or supports 3.0 (used in Initial Review, Second Review).
Nodes used (6)
- Manual Trigger
n8n-nodes-base.manualTrigger - Edit Fields (Set)
n8n-nodes-base.set - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Goto Human
@gotohuman/n8n-nodes-gotohuman.gotoHuman - OpenAI
@n8n/n8n-nodes-langchain.openAi - If
n8n-nodes-base.if
From the author
This n8n workflow automates the process of generating AI images using OpenAI's DALL-E 2 model with built-in human review and quality control. The workflow creates an image based on a predefined prompt, sends it for human review, and if the image is rejected,…