Move refiner tests into dedicated section

This commit is contained in:
Morpheus
2026-10-28 21:14:07 +00:00
parent 446f269a08
commit 2971e4579a
16 changed files with 11 additions and 9 deletions
+2 -2
View File
@@ -1,8 +1,8 @@
# I2I workflows
Use [`flux/`](flux/), [`qwen/`](qwen/), or [`flux3klein/`](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/`](qwen-noctq-flux3klein-refiner/) workflow chains a local Qwen NoctQ v4 generation into a low-denoise FLUX.3 Klein refinement pass.
Use [`flux/`](flux/), [`qwen/`](qwen/), or [`flux3klein/`](flux3klein/) for one-reference-image transformations. The workflows infer the subject from the input image instead of naming a specific character or scene. Refiner comparisons are maintained separately in [`../I2IPlusRefiner/`](../I2IPlusRefiner/).
The shared reference asset and static variables are recorded in [`variables.json`](variables.json) and `character_reference.png`. The test plans live in each model README. General edit-plus-refiner comparisons are in [`refiner/`](refiner/).
The shared reference asset and static variables are recorded in [`variables.json`](variables.json) and `character_reference.png`. The test plans live in each model README.
## Current best

Before

Width:  |  Height:  |  Size: 104 KiB

After

Width:  |  Height:  |  Size: 104 KiB

Before

Width:  |  Height:  |  Size: 2.8 MiB

After

Width:  |  Height:  |  Size: 2.8 MiB

@@ -3,9 +3,9 @@
"status": "completed",
"prompt_id": "a1415b9d-e126-4daa-8da6-0df771beb0b5",
"server": "http://192.168.1.202:8188",
"input_image": "../refiner_reference.jpg",
"input_image": "refiner_reference.jpg",
"input_image_sha256": "f478ab8064bd0642401cbf6bab9aa95380ed4c05d50c6d2959bc9a0eb632354a",
"prompt_source": "../qwen/workflow.json#7",
"prompt_source": "../I2I/qwen/workflow.json#7",
"prompt_used_by_base": true,
"prompt_used_by_refiner": false,
"base_stage": {

Before

Width:  |  Height:  |  Size: 2.5 MiB

After

Width:  |  Height:  |  Size: 2.5 MiB

Before

Width:  |  Height:  |  Size: 2.5 MiB

After

Width:  |  Height:  |  Size: 2.5 MiB

@@ -3,9 +3,9 @@
"status": "completed",
"prompt_id": "f8e14f3e-68f6-4034-b8aa-b039b475a8b5",
"server": "http://192.168.1.202:8188",
"input_image": "../refiner_reference.jpg",
"input_image": "refiner_reference.jpg",
"input_image_sha256": "f478ab8064bd0642401cbf6bab9aa95380ed4c05d50c6d2959bc9a0eb632354a",
"prompt_source": "../qwen/workflow.json#7",
"prompt_source": "../I2I/qwen/workflow.json#7",
"prompt_used_by_base": true,
"prompt_used_by_refiner": false,
"base_stage": {

Before

Width:  |  Height:  |  Size: 2.3 MiB

After

Width:  |  Height:  |  Size: 2.3 MiB

Before

Width:  |  Height:  |  Size: 2.1 MiB

After

Width:  |  Height:  |  Size: 2.1 MiB

@@ -3,9 +3,9 @@
"status": "completed",
"prompt_id": "5fd70f61-ff39-46f4-a38e-730ba4ac84c8",
"server": "http://192.168.1.202:8188",
"input_image": "../refiner_reference.jpg",
"input_image": "refiner_reference.jpg",
"input_image_sha256": "f478ab8064bd0642401cbf6bab9aa95380ed4c05d50c6d2959bc9a0eb632354a",
"prompt_source": "../qwen/workflow.json#7",
"prompt_source": "../I2I/qwen/workflow.json#7",
"prompt_used_by_base": true,
"prompt_used_by_refiner": false,
"base_stage": {

Before

Width:  |  Height:  |  Size: 2.1 MiB

After

Width:  |  Height:  |  Size: 2.1 MiB

@@ -2,7 +2,7 @@
"workflow": "I2I plus refiner",
"input_image": "refiner_reference.jpg",
"input_image_sha256": "f478ab8064bd0642401cbf6bab9aa95380ed4c05d50c6d2959bc9a0eb632354a",
"prompt_source": "../qwen/workflow.json#7 (canonical shared I2I prompt)",
"prompt_source": "../I2I/qwen/workflow.json#7 (canonical shared I2I prompt)",
"resolution": {"width": 1080, "height": 1920},
"base_stage": {
"model": "qwen_image_2.1_int8_convrot.safetensors",
+1
View File
@@ -13,6 +13,7 @@ This directory contains the best tested workflows for the available hardware. Ch
- [`flux/`](I2I/flux/) — Flux.2 Klein photorealistic conversion.
- [`qwen/`](I2I/qwen/) — Qwen Image 2.1 photorealistic conversion.
- [`flux3klein/`](I2I/flux3klein/) — FLUX.3 Klein reference-image tests.
- [`I2IPlusRefiner/`](I2IPlusRefiner/) — edit-model output followed by a separate refiner, with base/refined image pairs.
- [`MultipleRef2I/`](MultipleRef2I/) — multi-reference image composition.
- [`flux/`](MultipleRef2I/flux/) — Flux.2 Klein best multi-reference workflow.
- [`flux3klein/`](MultipleRef2I/flux3klein/) — FLUX.3 Klein multi-reference tests.
+1
View File
@@ -13,6 +13,7 @@ matrix; visual review must use the same category fixtures and resolution.
| I2I | Flux.2 Klein | `character_reference.png` + shared I2I prompt | 1080×1920 category target | Matrix planned/untested | Candidate baseline |
| I2I | Qwen Image 2.1 | `character_reference.png` + shared I2I prompt | 1080×1920 category target | 34-row matrix recorded | Existing best recorded in category README |
| I2I | FLUX.3 Klein | same canonical I2I fixtures | 1080×1920 | Completed: CFG sweep + sampler matrix | New candidate |
| I2IPlusRefiner | Qwen Image 2.1 → FLUX.3 Klein | `refiner_reference.jpg` + canonical I2I prompt | Base 1080×1920; refined 1072×1920 | 3 comparison runs recorded | Refiner comparison section |
| MultipleRef2I | Flux.2 Klein | `person_reference.png` + `scene_reference.png` + shared prompt | 1920×1080 | Matrix planned/untested | Candidate baseline |
| MultipleRef2I | Qwen Image 2.1 | `person_reference.png` + `scene_reference.png` + shared prompt | 1920×1080 | 18-row matrix planned | New candidate |
| MultipleRef2I | FLUX.3 Klein | same canonical multi-reference fixtures | 1920×1080 | Completed: sampler matrix | New candidate |