diff --git a/prompts/README.md b/prompts/README.md index cfd33d9..3093241 100644 --- a/prompts/README.md +++ b/prompts/README.md @@ -8,8 +8,8 @@ through visual iterations without changing the underlying baseline. - `README.md` — purpose, input assumptions, expected output, and evaluation notes. - `prompt.txt` — reusable positive prompt. -- `workflow.json` — API-format workflow used for the prompt. -- `ui-workflow.json` — editable ComfyUI graph when available. +- `workflow-reference.md` — the maintained workflow to use; workflows are not + duplicated inside prompt folders. - `results/` — generated images and matching metadata records. ## Prompts diff --git a/prompts/person-to-clothing-flatlay/README.md b/prompts/person-to-clothing-flatlay/README.md index 0f1b323..91cc687 100644 --- a/prompts/person-to-clothing-flatlay/README.md +++ b/prompts/person-to-clothing-flatlay/README.md @@ -20,8 +20,11 @@ This prompt starts from the current best Qwen Image 2.1 I2I workflow: - Output: portrait 1080×1920 baseline, adjustable for composition - Reference input: one image containing the person and outfit -The copied workflow files preserve this starting point. The optimized Qwen -workflow remains the source of truth for future baseline changes. +Use the maintained workflow directly; it is intentionally not duplicated in +this prompt folder. The optimized Qwen workflow remains the source of truth +for future baseline changes. + +See [`workflow-reference.md`](workflow-reference.md). ## Expected result diff --git a/prompts/person-to-clothing-flatlay/ui-workflow.json b/prompts/person-to-clothing-flatlay/ui-workflow.json deleted file mode 100644 index 6b32e12..0000000 --- a/prompts/person-to-clothing-flatlay/ui-workflow.json +++ /dev/null @@ -1,28 +0,0 @@ -{ - "id": "qwen-image-2.1-photorealistic-i2i-ui", - "revision": 0, - "last_node_id": 15, - "last_link_id": 18, - "nodes": [ - {"id":1,"type":"UNETLoader","pos":[-900,0],"size":[360,110],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[{"name":"MODEL","type":"MODEL","links":[1]}],"properties":{"Node name for S&R":"UNETLoader"},"widgets_values":["qwen_image_2.1_int8_convrot.safetensors","default"]}, - {"id":2,"type":"CLIPLoader","pos":[-900,180],"size":[360,150],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"CLIP","type":"CLIP","links":[2]}],"properties":{"Node name for S&R":"CLIPLoader"},"widgets_values":["qwen3vl_8b_w4a8.safetensors","qwen_image","default"]}, - {"id":3,"type":"VAELoader","pos":[-900,390],"size":[360,110],"flags":{},"order":2,"mode":0,"inputs":[],"outputs":[{"name":"VAE","type":"VAE","links":[3,4]}],"properties":{"Node name for S&R":"VAELoader"},"widgets_values":["qwen_image_2.1_vae_bf16.safetensors"]}, - {"id":4,"type":"LoadImage","pos":[-900,600],"size":[360,420],"flags":{},"order":3,"mode":0,"inputs":[],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[5]}],"properties":{"Node name for S&R":"LoadImage"},"widgets_values":["character_reference.png"]}, - {"id":5,"type":"ResizeAndPadImage","pos":[-420,620],"size":[320,190],"flags":{},"order":4,"mode":0,"inputs":[{"name":"image","type":"IMAGE","link":5}],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[6]}],"properties":{"Node name for S&R":"ResizeAndPadImage"},"widgets_values":[576,1024,"white","lanczos"]}, - {"id":6,"type":"QwenImage21Cache","pos":[-420,0],"size":[300,130],"flags":{},"order":5,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":1}],"outputs":[{"name":"MODEL","type":"MODEL","links":[7,8]}],"properties":{"Node name for S&R":"QwenImage21Cache"},"widgets_values":["auto","int8"]}, - {"id":7,"type":"TextEncodeQwenImage21","pos":[0,220],"size":[650,470],"flags":{},"order":6,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":2},{"name":"vae","type":"VAE","link":3},{"name":"image_1","type":"IMAGE","link":6}],"outputs":[{"name":"positive","type":"CONDITIONING","links":[9]},{"name":"negative","type":"CONDITIONING","links":[10]},{"name":"latent","type":"LATENT","links":[11]}],"properties":{"Node name for S&R":"TextEncodeQwenImage21"},"widgets_values":["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.","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",0]}, - {"id":8,"type":"KSamplerSelect","pos":[760,0],"size":[280,90],"flags":{},"order":7,"mode":0,"inputs":[],"outputs":[{"name":"SAMPLER","type":"SAMPLER","links":[12]}],"properties":{"Node name for S&R":"KSamplerSelect"},"widgets_values":["euler_cfg_pp"]}, - {"id":9,"type":"BasicScheduler","pos":[760,150],"size":[300,150],"flags":{},"order":8,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":7}],"outputs":[{"name":"SIGMAS","type":"SIGMAS","links":[13]}],"properties":{"Node name for S&R":"BasicScheduler"},"widgets_values":["beta",50,1]}, - {"id":10,"type":"RandomNoise","pos":[760,360],"size":[280,90],"flags":{},"order":9,"mode":0,"inputs":[],"outputs":[{"name":"NOISE","type":"NOISE","links":[14]}],"properties":{"Node name for S&R":"RandomNoise"},"widgets_values":[20260921]}, - {"id":11,"type":"CFGGuider","pos":[1120,120],"size":[300,150],"flags":{},"order":10,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":8},{"name":"positive","type":"CONDITIONING","link":9},{"name":"negative","type":"CONDITIONING","link":10}],"outputs":[{"name":"GUIDER","type":"GUIDER","links":[15]}],"properties":{"Node name for S&R":"CFGGuider"},"widgets_values":[3.5]}, - {"id":12,"type":"SamplerCustomAdvanced","pos":[1480,120],"size":[320,220],"flags":{},"order":11,"mode":0,"inputs":[{"name":"noise","type":"NOISE","link":14},{"name":"guider","type":"GUIDER","link":15},{"name":"sampler","type":"SAMPLER","link":12},{"name":"sigmas","type":"SIGMAS","link":13},{"name":"latent_image","type":"LATENT","link":11}],"outputs":[{"name":"output","type":"LATENT","links":[16]}],"properties":{"Node name for S&R":"SamplerCustomAdvanced"},"widgets_values":[]}, - {"id":13,"type":"VAEDecode","pos":[1850,120],"size":[260,110],"flags":{},"order":12,"mode":0,"inputs":[{"name":"samples","type":"LATENT","link":16},{"name":"vae","type":"VAE","link":4}],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[17]}],"properties":{"Node name for S&R":"VAEDecode"},"widgets_values":[]}, - {"id":14,"type":"ResizeAndPadImage","pos":[2160,120],"size":[320,190],"flags":{},"order":13,"mode":0,"inputs":[{"name":"image","type":"IMAGE","link":17}],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[18]}],"properties":{"Node name for S&R":"ResizeAndPadImage"},"widgets_values":[1080,1920,"white","lanczos"]}, - {"id":15,"type":"SaveImage","pos":[2540,120],"size":[320,110],"flags":{},"order":14,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":18}],"outputs":[],"properties":{"Node name for S&R":"SaveImage"},"widgets_values":["fluxExperiments/imageEdit/qwen_i2i"]} - ], - "links": [[1,1,0,6,0,"MODEL"],[2,2,0,7,0,"CLIP"],[3,3,0,7,1,"VAE"],[4,3,0,13,1,"VAE"],[5,4,0,5,0,"IMAGE"],[6,5,0,7,2,"IMAGE"],[7,6,0,9,0,"MODEL"],[8,6,0,11,0,"MODEL"],[9,7,0,11,1,"CONDITIONING"],[10,7,1,11,2,"CONDITIONING"],[11,7,2,12,4,"LATENT"],[12,8,0,12,2,"SAMPLER"],[13,9,0,12,3,"SIGMAS"],[14,10,0,12,0,"NOISE"],[15,11,0,12,1,"GUIDER"],[16,12,0,13,0,"LATENT"],[17,13,0,14,0,"IMAGE"],[18,14,0,15,0,"IMAGE"]], - "groups": [], - "config": {}, - "extra": {"note":"Qwen Image 2.1 photorealistic I2I; current best Q-I2I-34; 1080x1920 output"}, - "version": 0.4 -} diff --git a/prompts/person-to-clothing-flatlay/workflow-reference.md b/prompts/person-to-clothing-flatlay/workflow-reference.md new file mode 100644 index 0000000..c378c28 --- /dev/null +++ b/prompts/person-to-clothing-flatlay/workflow-reference.md @@ -0,0 +1,10 @@ +# Workflow reference + +Use the maintained best Qwen I2I workflow: + +- API workflow: [`optimized/I2I/qwen/workflow.json`](../../../optimized/I2I/qwen/workflow.json) +- ComfyUI editor workflow: [`optimized/I2I/qwen/ui-workflow.json`](../../../optimized/I2I/qwen/ui-workflow.json) + +Do not copy either workflow into this prompt folder. Prompt experiments use +the current maintained workflow so improvements to the Qwen baseline apply to +all generic prompts. diff --git a/prompts/person-to-clothing-flatlay/workflow.json b/prompts/person-to-clothing-flatlay/workflow.json deleted file mode 100644 index 18e58ac..0000000 --- a/prompts/person-to-clothing-flatlay/workflow.json +++ /dev/null @@ -1,17 +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":"character_reference.png"}}, - "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}}, - "10": {"class_type":"RandomNoise","inputs":{"noise_seed":20260921}}, - "11": {"class_type":"CFGGuider","inputs":{"model":["6",0],"positive":["7",0],"negative":["7",1],"cfg":3.5}}, - "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]}}, - "14": {"class_type":"ResizeAndPadImage","inputs":{"image":["13",0],"target_width":1080,"target_height":1920,"padding_color":"white","interpolation":"lanczos"}}, - "15": {"class_type":"SaveImage","inputs":{"images":["14",0],"filename_prefix":"fluxExperiments/imageEdit/qwen_i2i"}} -}