19 lines
1.2 KiB
Markdown
19 lines
1.2 KiB
Markdown
# T2I workflows
|
||
|
||
Use [`flux/`](flux/) or [`qwen/`](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`](variables.json). The test plans live in each model README.
|
||
|
||
The shared comparison prompt is [`prompt.txt`](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 A result is only promoted to **Current Best** after visual review; the previous Qwen result below is retained as a historical reference but is superseded by the direct high-resolution workflow reset.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| Qwen Image 2.1 | Q-T2I-01 | 198.1 s | [Q-T2I-01.png](qwen/results/Q-T2I-01.png) | Historical 1080×1920 result; superseded |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.
|