T2I workflows
Use flux/, qwen/, flux3image/, or ideogram/ for text-to-image baselines. Prompts and seeds are fixed for cross-model comparison; sampler, scheduler, CFG, steps, and explicitly labelled scaling-study resolutions 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.
| Model | Best so far | Runtime | Generated image | Status |
|---|---|---|---|---|
| Flux.2 Klein | F-T2I-03 | 220.3 s | F-T2I-03.png | Current best; 1080×1920 target |
| Qwen Image 2.1 | Q-T2I-57 | 110.2 s | Q-T2I-57.png | Current best; direct 1088×1920 latent; res_multistep, beta, 25 steps, CFG 2.5 |
| FLUX.3 Klein | F3I-T2I-01 / sampler matrix | recorded | best5 | Complete local matrix; canonical comparison resolution 1088×1920; visual cross-model ranking pending |
| Ideogram 4 | MAG-MATRIX-24 | 30.154 s | MAG-MATRIX-24.png | Complete magazine-cover matrix; different structured prompt, not directly comparable to the shared portrait prompt |
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.