Save base and refined I2I outputs

This commit is contained in:
Morpheus
2026-10-28 20:39:21 +00:00
parent 664812cba1
commit 5668acbdea
5 changed files with 29 additions and 13 deletions
+4 -3
View File
@@ -2,8 +2,9 @@
This section contains image-to-image workflows where an edit model creates the
first image and a separate refiner improves its surface quality, texture, and
photorealism. The input image and canonical I2I prompt remain fixed when
comparing refiner models.
photorealism. Each run saves both the base-stage image and the refined image.
The input image and canonical I2I prompt remain fixed when comparing refiner
models.
## Current test
@@ -14,7 +15,7 @@ text prompt, so it cannot replace the subject from text conditioning.
| ID | Input | Prompt | Base stage | Refiner stage | Resolution | Generation time (s) | Status | Review |
|---|---|---|---|---|---:|---:|---|---|
| QRF-I2I-01 | `refiner_reference.jpg` | Canonical shared I2I prompt | NoctQ v4, 8 steps, CFG 1, Euler ancestral / beta | FLUX.3 Klein, 8 steps, guidance 1, Euler ancestral / simple, denoise 0.11 | 1088×1920 | 115.720 | Completed | Subject preserved; illustrated/stylized baseline; [PNG](results/QRF-I2I-01.png) |
| QRF-I2I-01 | `refiner_reference.jpg` | Canonical shared I2I prompt | NoctQ v4, 8 steps, CFG 1, Euler ancestral / beta | FLUX.3 Klein, 8 steps, guidance 1, Euler ancestral / simple, denoise 0.11 | 1088×1920 | 115.720 uncached; 0.274 cached | Completed | Base and refined outputs are nearly identical at denoise 0.11; [base PNG](results/QRF-I2I-01-base.png) vs [refined PNG](results/QRF-I2I-01.png) |
## Planned follow-ups