Wavemaker Blog
Page 12 of 18
RSS feed-
Memoized Workflow Runs: Why Changing the Last Step Should Not Re-Bill the First
Wavemaker content-addresses block outputs per org — identical inputs hit the memo cache, while retryUntil and bestOfN use instance salt. How memoization makes iterative workflow runs affordable.
-
LoRA Dataset Preparation: Curation, Captions, and Safety Gates
How to prepare image, video, and voice datasets for Wavemaker LoRA training—counts, captions, moderation, and promote-from-runs workflows that beat raw folder dumps.
-
Web-Based ComfyUI Alternatives in 2026 (What Actually Runs Online)
Compare web-based ComfyUI alternatives: hosted Comfy runtimes vs transpile-to-platform workflows. Claim-safe guide — no pixel parity, no custom-node execution on Wavemaker.
-
Quality Contracts for AI Pipelines: Retry Until, Review Facts, and No Silent Give-Ups
Quality contracts are visible combinator nodes — retryUntil and bestOfN — wired to review_image facts, memo-salted so rejected outputs cannot cache-loop. How Wavemaker encodes them in WorkflowSpec.