1.1 KiB
I2I workflows
Use flux/, qwen/, or flux3klein/ for one-reference-image transformations. The workflows infer the subject from the input image instead of naming a specific character or scene. The qwen-noctq-flux3klein-refiner/ workflow chains a local Qwen NoctQ v4 generation into a low-denoise FLUX.3 Klein refinement pass.
The shared reference asset and static variables are recorded in variables.json and character_reference.png. The test plans live in each model README. General edit-plus-refiner comparisons are in refiner/.
Current best
Qwen I2I: qwen/ — Q-I2I-34, Euler CFG++, beta scheduler, 50 steps,
CFG 3.5, approximately 68.3 seconds.
FLUX.3 Klein: flux3klein/ — planned against the same
character_reference.png and shared I2I prompt at a fixed 1080×1920 output;
not yet run.
Store each I2I test under the selected model's results/<test-id>.png and results/<test-id>.json using the table ID as the label.