diff --git a/optimized/I2I/refiner/README.md b/optimized/I2I/refiner/README.md index cc37a2b..f241851 100644 --- a/optimized/I2I/refiner/README.md +++ b/optimized/I2I/refiner/README.md @@ -17,6 +17,7 @@ text prompt, so it cannot replace the subject from text conditioning. |---|---|---|---|---|---:|---:|---|---| | 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 diff --git a/optimized/I2I/refiner/results/QRF-I2I-03-base.png b/optimized/I2I/refiner/results/QRF-I2I-03-base.png new file mode 100644 index 0000000..7e31388 Binary files /dev/null and b/optimized/I2I/refiner/results/QRF-I2I-03-base.png differ diff --git a/optimized/I2I/refiner/results/QRF-I2I-03.json b/optimized/I2I/refiner/results/QRF-I2I-03.json new file mode 100644 index 0000000..3e837a9 --- /dev/null +++ b/optimized/I2I/refiner/results/QRF-I2I-03.json @@ -0,0 +1,49 @@ +{ + "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." +} diff --git a/optimized/I2I/refiner/results/QRF-I2I-03.png b/optimized/I2I/refiner/results/QRF-I2I-03.png new file mode 100644 index 0000000..4e5dc99 Binary files /dev/null and b/optimized/I2I/refiner/results/QRF-I2I-03.png differ diff --git a/optimized/I2I/refiner/variables.json b/optimized/I2I/refiner/variables.json index e54298f..11fcbb8 100644 --- a/optimized/I2I/refiner/variables.json +++ b/optimized/I2I/refiner/variables.json @@ -46,6 +46,16 @@ "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" } ] } diff --git a/optimized/I2I/refiner/workflow.json b/optimized/I2I/refiner/workflow.json index fe329c5..a4316de 100644 --- a/optimized/I2I/refiner/workflow.json +++ b/optimized/I2I/refiner/workflow.json @@ -6,10 +6,10 @@ "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_cfg_pp"}}, - "9": {"class_type":"BasicScheduler","inputs":{"model":["6",0],"scheduler":"beta","steps":50,"denoise":1.0}}, + "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":3.5}}, + "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"}}, @@ -25,6 +25,6 @@ "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-02-base"}}, - "26": {"class_type":"SaveImage","inputs":{"images":["25",0],"filename_prefix":"fluxExperiments/i2i_refiner/QRF-I2I-02"}} + "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"}} }