projects / swarmui-image-gen
SwarmUI Image Generation
A calibrated image-generation pipeline talking to SwarmUI on a 3090TI rig — 12 calibration rounds, 260+ graded samples, 18 curated model presets.
Overview
A calibration and generation pipeline for local Stable Diffusion image generation. Talks to SwarmUI on a Windows rig with an NVIDIA 3090TI via HTTP API.
Calibration methodology
12 rounds of systematic A/B testing across 12 models:
- Step sweeps — finding the sweet spot (Flux: 36 steps is perfect; Chroma: flat plateau 16-40)
- CFG sweeps — Chroma sweet spot is 2.5-3.5; outside that drops to 3.0/5 quality
- Cross-model comparisons — SDXL wins action/rain scenes at 5.0/5; Flux nails anime at 5.0/5
- Single-sample trap — Round 11 found a “winner” on one prompt; Round 12 with 3 new prompts disproved it. Rule: n≥3 prompts per cell to change a default.
Curated defaults
| Model | Steps | CFG | Sampler | Notes |
|---|---|---|---|---|
| flux1-dev-fp8 | 36 | — | euler/simple | 5.00/5 winner |
| chroma_v10HD | 24 | 3.0 | dpmpp_2m/beta | Cap at 40 steps |
| chroma1-base | 24 | 3.0 | dpmpp_2m/beta | Best for portraits |
| sdxl_base | 36 | 7.0 | dpmpp_2m/karras | Flat plateau 36-60 |
Hard-won lesson
Never trust a single-image calibration. A 1.0-point quality advantage on n=1 is noise. This methodology error almost became a permanent default change before a wider sweep caught it.