Move refiner tests into dedicated section
@@ -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
|
||||
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
# I2I plus refiner tests
|
||||
|
||||
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. 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
|
||||
|
||||
The first test used Qwen NoctQ v4. The follow-up uses the proven Qwen Image 2.1
|
||||
I2I stack and settings from `optimized/I2I/qwen/`, with the new reference image
|
||||
`refiner_reference.jpg`. The FLUX stage receives the Qwen pixels and has no
|
||||
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 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) |
|
||||
| QRF-I2I-02 | `refiner_reference.jpg` | Canonical shared I2I prompt | Qwen Image 2.1, 50 steps, CFG 3.5, Euler CFG++ / beta | FLUX.3 Klein, 8 steps, guidance 1, Euler ancestral / simple, denoise 0.11 | Base 1080×1920; refined 1072×1920 | 145.129 | Completed | More realistic base; [base PNG](results/QRF-I2I-02-base.png) vs [refined PNG](results/QRF-I2I-02.png) |
|
||||
| QRF-I2I-03 | `refiner_reference.jpg` | Canonical shared I2I prompt | Qwen Image 2.1, 8 steps, CFG 1, Euler ancestral / beta | FLUX.3 Klein, 8 steps, guidance 1, Euler ancestral / simple, denoise 0.11 | Base 1080×1920; refined 1072×1920 | 60.252 | Completed | Realistic low-step base; white top/bottom bands; [base PNG](results/QRF-I2I-03-base.png) vs [refined PNG](results/QRF-I2I-03.png) |
|
||||
|
||||
## Planned follow-ups
|
||||
|
||||
- ZImage as the refiner, using the same base output, prompt, input image, and
|
||||
resolution.
|
||||
- Additional refiner models only after the first comparison is recorded.
|
||||
|
||||
Record the resolved workflow, prompt ID, model names, runtime, dimensions,
|
||||
hashes, and visual review in `results/QRF-I2I-01.json`.
|
||||
|
Before Width: | Height: | Size: 104 KiB |
|
Before Width: | Height: | Size: 2.8 MiB |
@@ -1,49 +0,0 @@
|
||||
{
|
||||
"test_id": "QRF-I2I-01",
|
||||
"status": "completed",
|
||||
"prompt_id": "a1415b9d-e126-4daa-8da6-0df771beb0b5",
|
||||
"server": "http://192.168.1.202:8188",
|
||||
"input_image": "../refiner_reference.jpg",
|
||||
"input_image_sha256": "f478ab8064bd0642401cbf6bab9aa95380ed4c05d50c6d2959bc9a0eb632354a",
|
||||
"prompt_source": "../qwen/workflow.json#7",
|
||||
"prompt_used_by_base": true,
|
||||
"prompt_used_by_refiner": false,
|
||||
"base_stage": {
|
||||
"model": "NoctQ_V4_int8_convrot.safetensors",
|
||||
"text_encoder": "qwen3vl_8b_w4a8.safetensors",
|
||||
"vae": "qwen_image_2.1_vae_bf16.safetensors",
|
||||
"steps": 8,
|
||||
"cfg": 1.0,
|
||||
"sampler": "euler_ancestral",
|
||||
"scheduler": "beta",
|
||||
"denoise": 1.0
|
||||
},
|
||||
"refiner_stage": {
|
||||
"model": "flux3-image-klein-int8-convrot.safetensors",
|
||||
"text_encoder": "qwen3-vl-4b-heretic_int8.safetensors",
|
||||
"vae": "flux2-vae.safetensors",
|
||||
"steps": 8,
|
||||
"guidance": 1.0,
|
||||
"sampler": "euler_ancestral",
|
||||
"scheduler": "simple",
|
||||
"denoise": 0.11
|
||||
},
|
||||
"generation_time_seconds": 0.274,
|
||||
"uncached_generation_time_seconds": 115.72,
|
||||
"cache_hit": true,
|
||||
"outputs": {
|
||||
"base": {
|
||||
"path": "results/QRF-I2I-01-base.png",
|
||||
"width": 1088,
|
||||
"height": 1920,
|
||||
"sha256": "39c89ebdf98f957cc074e77195031158046de10f2aecb931509e96c3e906828c"
|
||||
},
|
||||
"refined": {
|
||||
"path": "results/QRF-I2I-01.png",
|
||||
"width": 1088,
|
||||
"height": 1920,
|
||||
"sha256": "41c4f29da54c0f8dd912525168a1661d70285902a19e5f8e08369beeac598241"
|
||||
}
|
||||
},
|
||||
"review": "The new reference image was used correctly. Both outputs preserve the black man with curly hair, glasses, earring, white shirt, tie, and dark waistcoat. At denoise 0.11 the base and refined images are visually extremely similar; the output remains illustrated/stylized rather than fully photorealistic."
|
||||
}
|
||||
|
Before Width: | Height: | Size: 2.5 MiB |
|
Before Width: | Height: | Size: 2.5 MiB |
@@ -1,49 +0,0 @@
|
||||
{
|
||||
"test_id": "QRF-I2I-02",
|
||||
"status": "completed",
|
||||
"prompt_id": "f8e14f3e-68f6-4034-b8aa-b039b475a8b5",
|
||||
"server": "http://192.168.1.202:8188",
|
||||
"input_image": "../refiner_reference.jpg",
|
||||
"input_image_sha256": "f478ab8064bd0642401cbf6bab9aa95380ed4c05d50c6d2959bc9a0eb632354a",
|
||||
"prompt_source": "../qwen/workflow.json#7",
|
||||
"prompt_used_by_base": true,
|
||||
"prompt_used_by_refiner": false,
|
||||
"base_stage": {
|
||||
"model": "qwen_image_2.1_int8_convrot.safetensors",
|
||||
"text_encoder": "qwen3vl_8b_w4a8.safetensors",
|
||||
"vae": "qwen_image_2.1_vae_bf16.safetensors",
|
||||
"generation_width": 576,
|
||||
"generation_height": 1024,
|
||||
"steps": 50,
|
||||
"cfg": 3.5,
|
||||
"sampler": "euler_cfg_pp",
|
||||
"scheduler": "beta",
|
||||
"denoise": 1.0
|
||||
},
|
||||
"refiner_stage": {
|
||||
"model": "flux3-image-klein-int8-convrot.safetensors",
|
||||
"text_encoder": "qwen3-vl-4b-heretic_int8.safetensors",
|
||||
"vae": "flux2-vae.safetensors",
|
||||
"steps": 8,
|
||||
"guidance": 1.0,
|
||||
"sampler": "euler_ancestral",
|
||||
"scheduler": "simple",
|
||||
"denoise": 0.11
|
||||
},
|
||||
"generation_time_seconds": 145.129,
|
||||
"outputs": {
|
||||
"base": {
|
||||
"path": "results/QRF-I2I-02-base.png",
|
||||
"width": 1080,
|
||||
"height": 1920,
|
||||
"sha256": "72e9732793552a8efedd5775d4cc1dfe2e9035e1430a03d786ef40ffdb5c9bb3"
|
||||
},
|
||||
"refined": {
|
||||
"path": "results/QRF-I2I-02.png",
|
||||
"width": 1072,
|
||||
"height": 1920,
|
||||
"sha256": "d6b61c3cb096fdb31ad83cd9789a9cfd13cfbd2e624085af9dd611dd7cc3fa63"
|
||||
}
|
||||
},
|
||||
"review": "The real Qwen Image 2.1 base produces a substantially more realistic result than QRF-I2I-01. The subject, curly hair, glasses, earring, shirt, tie, and waistcoat are preserved. The FLUX low-denoise refinement remains very close to the base output, with no subject substitution."
|
||||
}
|
||||
|
Before Width: | Height: | Size: 2.3 MiB |
|
Before Width: | Height: | Size: 2.1 MiB |
@@ -1,49 +0,0 @@
|
||||
{
|
||||
"test_id": "QRF-I2I-03",
|
||||
"status": "completed",
|
||||
"prompt_id": "5fd70f61-ff39-46f4-a38e-730ba4ac84c8",
|
||||
"server": "http://192.168.1.202:8188",
|
||||
"input_image": "../refiner_reference.jpg",
|
||||
"input_image_sha256": "f478ab8064bd0642401cbf6bab9aa95380ed4c05d50c6d2959bc9a0eb632354a",
|
||||
"prompt_source": "../qwen/workflow.json#7",
|
||||
"prompt_used_by_base": true,
|
||||
"prompt_used_by_refiner": false,
|
||||
"base_stage": {
|
||||
"model": "qwen_image_2.1_int8_convrot.safetensors",
|
||||
"text_encoder": "qwen3vl_8b_w4a8.safetensors",
|
||||
"vae": "qwen_image_2.1_vae_bf16.safetensors",
|
||||
"generation_width": 576,
|
||||
"generation_height": 1024,
|
||||
"steps": 8,
|
||||
"cfg": 1.0,
|
||||
"sampler": "euler_ancestral",
|
||||
"scheduler": "beta",
|
||||
"denoise": 1.0
|
||||
},
|
||||
"refiner_stage": {
|
||||
"model": "flux3-image-klein-int8-convrot.safetensors",
|
||||
"text_encoder": "qwen3-vl-4b-heretic_int8.safetensors",
|
||||
"vae": "flux2-vae.safetensors",
|
||||
"steps": 8,
|
||||
"guidance": 1.0,
|
||||
"sampler": "euler_ancestral",
|
||||
"scheduler": "simple",
|
||||
"denoise": 0.11
|
||||
},
|
||||
"generation_time_seconds": 60.252,
|
||||
"outputs": {
|
||||
"base": {
|
||||
"path": "results/QRF-I2I-03-base.png",
|
||||
"width": 1080,
|
||||
"height": 1920,
|
||||
"sha256": "5dda976910f6a3a5e168ea2534dc73b00983b15a8c0e9bdd780a3f8c44ae38bc"
|
||||
},
|
||||
"refined": {
|
||||
"path": "results/QRF-I2I-03.png",
|
||||
"width": 1072,
|
||||
"height": 1920,
|
||||
"sha256": "ff9d32cebb4e1ad047a1a447a06517517c87d8abf21932e87e2d633e4037212a"
|
||||
}
|
||||
},
|
||||
"review": "The real Qwen Image 2.1 base at CFG 1 and 8 steps produces a realistic portrait and preserves the subject. The FLUX refinement remains very close at denoise 0.11. Both outputs include white top/bottom bands from the low-step Qwen composition and should be compared against QRF-I2I-02."
|
||||
}
|
||||
|
Before Width: | Height: | Size: 2.1 MiB |
@@ -1,61 +0,0 @@
|
||||
{
|
||||
"workflow": "I2I plus refiner",
|
||||
"input_image": "refiner_reference.jpg",
|
||||
"input_image_sha256": "f478ab8064bd0642401cbf6bab9aa95380ed4c05d50c6d2959bc9a0eb632354a",
|
||||
"prompt_source": "../qwen/workflow.json#7 (canonical shared I2I prompt)",
|
||||
"resolution": {"width": 1080, "height": 1920},
|
||||
"base_stage": {
|
||||
"model": "qwen_image_2.1_int8_convrot.safetensors",
|
||||
"text_encoder": "qwen3vl_8b_w4a8.safetensors",
|
||||
"vae": "qwen_image_2.1_vae_bf16.safetensors",
|
||||
"steps": 50,
|
||||
"cfg": 3.5,
|
||||
"sampler": "euler_cfg_pp",
|
||||
"scheduler": "beta",
|
||||
"denoise": 1.0
|
||||
},
|
||||
"refiner_stage": {
|
||||
"model": "flux3-image-klein-int8-convrot.safetensors",
|
||||
"text_encoder": "qwen3-vl-4b-heretic_int8.safetensors",
|
||||
"vae": "flux2-vae.safetensors",
|
||||
"steps": 8,
|
||||
"guidance": 1.0,
|
||||
"sampler": "euler_ancestral",
|
||||
"scheduler": "simple",
|
||||
"denoise": 0.11
|
||||
},
|
||||
"status": "completed",
|
||||
"results": [
|
||||
{
|
||||
"id": "QRF-I2I-01",
|
||||
"status": "completed",
|
||||
"generation_time_seconds": 0.274,
|
||||
"uncached_generation_time_seconds": 115.72,
|
||||
"outputs": {
|
||||
"base": "results/QRF-I2I-01-base.png",
|
||||
"refined": "results/QRF-I2I-01.png"
|
||||
},
|
||||
"metadata": "results/QRF-I2I-01.json"
|
||||
},
|
||||
{
|
||||
"id": "QRF-I2I-02",
|
||||
"status": "completed",
|
||||
"generation_time_seconds": 145.129,
|
||||
"outputs": {
|
||||
"base": "results/QRF-I2I-02-base.png",
|
||||
"refined": "results/QRF-I2I-02.png"
|
||||
},
|
||||
"metadata": "results/QRF-I2I-02.json"
|
||||
},
|
||||
{
|
||||
"id": "QRF-I2I-03",
|
||||
"status": "completed",
|
||||
"generation_time_seconds": 60.252,
|
||||
"outputs": {
|
||||
"base": "results/QRF-I2I-03-base.png",
|
||||
"refined": "results/QRF-I2I-03.png"
|
||||
},
|
||||
"metadata": "results/QRF-I2I-03.json"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,30 +0,0 @@
|
||||
{
|
||||
"1": {"class_type":"UNETLoader","inputs":{"unet_name":"qwen_image_2.1_int8_convrot.safetensors","weight_dtype":"default"}},
|
||||
"2": {"class_type":"CLIPLoader","inputs":{"clip_name":"qwen3vl_8b_w4a8.safetensors","type":"qwen_image","device":"default"}},
|
||||
"3": {"class_type":"VAELoader","inputs":{"vae_name":"qwen_image_2.1_vae_bf16.safetensors"}},
|
||||
"4": {"class_type":"LoadImage","inputs":{"image":"refiner_reference.jpg"}},
|
||||
"5": {"class_type":"ResizeAndPadImage","inputs":{"image":["4",0],"target_width":576,"target_height":1024,"padding_color":"white","interpolation":"lanczos"}},
|
||||
"6": {"class_type":"QwenImage21Cache","inputs":{"model":["1",0],"device":"auto","dtype":"int8"}},
|
||||
"7": {"class_type":"TextEncodeQwenImage21","inputs":{"clip":["2",0],"prompt":"Transform the supplied reference image into a photorealistic image of the same subject. Infer identity, facial features, skin tone, hairstyle, clothing, accessories, colors, pose, body proportions, composition, and framing directly from the reference. Preserve those visual attributes faithfully while replacing the original rendering style with natural human anatomy, realistic skin and hair texture, physically accurate materials, believable fabric and surface detail, natural hands and fingers, cinematic soft light, realistic shadows, coherent perspective, premium editorial photography, high dynamic range, photorealistic, highly detailed. Do not redesign, restyle, substitute, add, remove, mirror, or crop the subject. No text or logos.","negative_prompt":"different person, changed identity, changed face, changed hairstyle, changed clothing, changed colors, altered accessories, changed pose, different composition, extra person, duplicate person, extra limbs, malformed hands, fused fingers, distorted anatomy, cropped head, cropped feet, mirrored image, cartoon, illustration, anime, CGI, plastic skin, waxy skin, blurry, low detail, text, logo, watermark","resolution":0,"images.image_1":["5",0],"vae":["3",0]}},
|
||||
"8": {"class_type":"KSamplerSelect","inputs":{"sampler_name":"euler_ancestral"}},
|
||||
"9": {"class_type":"BasicScheduler","inputs":{"model":["6",0],"scheduler":"beta","steps":8,"denoise":1.0}},
|
||||
"10": {"class_type":"RandomNoise","inputs":{"noise_seed":310101}},
|
||||
"11": {"class_type":"CFGGuider","inputs":{"model":["6",0],"positive":["7",0],"negative":["7",1],"cfg":1.0}},
|
||||
"12": {"class_type":"SamplerCustomAdvanced","inputs":{"noise":["10",0],"guider":["11",0],"sampler":["8",0],"sigmas":["9",0],"latent_image":["7",2]}},
|
||||
"13": {"class_type":"VAEDecode","inputs":{"samples":["12",0],"vae":["3",0]}},
|
||||
"28": {"class_type":"ResizeAndPadImage","inputs":{"image":["13",0],"target_width":1080,"target_height":1920,"padding_color":"white","interpolation":"lanczos"}},
|
||||
"14": {"class_type":"UNETLoader","inputs":{"unet_name":"flux3-image-klein-int8-convrot.safetensors","weight_dtype":"default"}},
|
||||
"15": {"class_type":"CLIPLoader","inputs":{"clip_name":"qwen3-vl-4b-heretic_int8.safetensors","type":"flux3","device":"default"}},
|
||||
"16": {"class_type":"VAELoader","inputs":{"vae_name":"flux2-vae.safetensors"}},
|
||||
"17": {"class_type":"StarFlux2Conditioner","inputs":{"clip":["15",0],"vae":["16",0],"text":"","join_references":true,"image_1":["28",0]}},
|
||||
"18": {"class_type":"FluxGuidance","inputs":{"conditioning":["17",0],"guidance":1.0}},
|
||||
"19": {"class_type":"BasicGuider","inputs":{"model":["14",0],"conditioning":["18",0]}},
|
||||
"20": {"class_type":"KSamplerSelect","inputs":{"sampler_name":"euler_ancestral"}},
|
||||
"21": {"class_type":"BasicScheduler","inputs":{"model":["14",0],"scheduler":"simple","steps":8,"denoise":0.11}},
|
||||
"22": {"class_type":"RandomNoise","inputs":{"noise_seed":310101}},
|
||||
"23": {"class_type":"VAEEncode","inputs":{"pixels":["28",0],"vae":["16",0]}},
|
||||
"24": {"class_type":"SamplerCustomAdvanced","inputs":{"noise":["22",0],"guider":["19",0],"sampler":["20",0],"sigmas":["21",0],"latent_image":["23",0]}},
|
||||
"25": {"class_type":"VAEDecode","inputs":{"samples":["24",0],"vae":["16",0]}},
|
||||
"27": {"class_type":"SaveImage","inputs":{"images":["28",0],"filename_prefix":"fluxExperiments/i2i_refiner/QRF-I2I-03-base"}},
|
||||
"26": {"class_type":"SaveImage","inputs":{"images":["25",0],"filename_prefix":"fluxExperiments/i2i_refiner/QRF-I2I-03"}}
|
||||
}
|
||||