1.2 KiB
T2I workflows
Use flux/ or qwen/ for the best tested text-to-image baseline. Prompts, seeds, and dimensions are intended to be replaced per task; sampler, scheduler, CFG, and steps are the optimization controls.
Static variables are recorded in variables.json. The test plans live in each model README.
The shared comparison prompt is prompt.txt; all T2I model workflows should use this prompt so model results remain directly comparable.
Best results so far
This summary is maintained across the model-specific test plans. A result is only promoted to Current Best after visual review; the previous Qwen result below is retained as a historical reference but is superseded by the direct high-resolution workflow reset.
| Model | Best so far | Runtime | Generated image | Status |
|---|---|---|---|---|
| Flux.2 Klein | None recorded for the shared comparison prompt | — | — | Awaiting first matrix result |
| Qwen Image 2.1 | Q-T2I-01 | 198.1 s | Q-T2I-01.png | Historical 1080×1920 result; superseded |
Store each T2I test under the selected model's results/<test-id>.png and results/<test-id>.json using the table ID as the label.