BlueFish AIAQI AI Intelligence
⌕
Official documentationNot tested by BlueFish

Run an image A/B test with an official workflow

Learn workflows and model files, then compare prompts one variable at a time.

Last checked:
A quick glossary

Models generate and reason. Agents use tools to work on tasks. A harness manages an agent’s environment. MCP connects tools and data. Skills are reusable task guidance.

Current task

Deliver 2 A/B images, 1 reloadable JSON, a model/license/settings sheet and 3 visual review notes; the same seed does not guarantee identical pixels across versions.

Prerequisites

Basic file skills; official ComfyUI, a specific image model supported by your hardware, and authorized references. Record license, size and hardware requirements before downloading.

Estimated time

Plan 3–5 sessions of 30–60 minutes; downloads and rendering are additional, not measured.

Validation

Original exercises based on reviewed official documentation; no model, device or regional runtime test performed.

Validation

Deliver 2 A/B images, 1 reloadable JSON, a model/license/settings sheet and 3 visual review notes; the same seed does not guarantee identical pixels across versions.

Limits & boundaries

Wrong model directory, mismatched encoder/VAE, unfixed seed or VRAM exhaustion; reduce size and batch first, without guaranteeing speed from GPU names.

Alternatives

comfyui

Cost

Not verified

Amounts unverified. Local software can use existing hardware; model licensing, VRAM, storage, electricity and labor are separate. Cloud, APIs or subscriptions may charge.

Implementation steps

  1. 01
    Load the official text-to-image template; check paths and nodes, saving model ID, license link and workflow JSON without unknown custom nodes.
  2. 02
    Fix model, size, seed and sampler settings; generate A/B images from an original still-life prompt, changing only lighting. Log queue time, inference time and failures.
  3. 03
    Reimport JSON to verify model and settings recovery; inspect composition and garbled text, removing private paths/prompts and saving a sanitized sharing copy.

Limits & boundaries

  • Original exercises based on reviewed official documentation; no model, device or regional runtime test performed.
  • Check input and model licenses individually; generated images are not automatically cleared for commercial use. PNG/JSON may contain prompts and paths; sanitize sharing copies.

Permissions & risks

  • Check input and model licenses individually; generated images are not automatically cleared for commercial use. PNG/JSON may contain prompts and paths; sanitize sharing copies.

Original sources

  1. ComfyUI first image tutorial ↗

    docs.comfy.org · 2026-10-16 · Official documentation

Connected resources

Integration platformFree software; check license and compute costs

ComfyUI

An open-source interface and backend organizing generative workflows through node graphs.

Official documentation