tts-voice-creator-clone-and.../workflows/comfyui-character-consistent-images.json
mARTin-B78 f7264a8c07 chore: release 1.21.0 - Consistent ComfyUI Character Renders and Audiobook Export
- Deterministic hash-based character portraits and reference sheets
- Implemented strict early Renaissance aesthetic controls and role-specific headwear rules
- Added audiobook batch export scripts and progress tooling
- Verified book profiles with a new 'confirmed' state tracking mechanism
- Updated Pillow dependency for robust image handling
- Configured .gitignore for audiobook and audio cache exports
2026-08-23 09:12:57 +02:00

653 lines
13 KiB
JSON

{
"1": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "qwen_image_edit_fp8_e4m3fn.safetensors",
"weight_dtype": "fp8_e4m3fn"
}
},
"2": {
"class_type": "CLIPLoader",
"inputs": {
"clip_name": "qwen_2.5_vl_7b_fp8_scaled.safetensors",
"type": "qwen_image",
"device": "default"
}
},
"3": {
"class_type": "VAELoader",
"inputs": {
"vae_name": "qwen_image_vae.safetensors"
}
},
"4": {
"class_type": "LoadImage",
"inputs": {
"image": "voice_creator_darrag_identity_v3.png"
}
},
"5": {
"class_type": "ImageCrop",
"inputs": {
"image": ["4", 0],
"width": 768,
"height": 768,
"x": 128,
"y": 0
}
},
"7": {
"class_type": "ImageScale",
"inputs": {
"image": ["5", 0],
"upscale_method": "lanczos",
"width": 1024,
"height": 1024,
"crop": "disabled"
}
},
"profile_save": {
"class_type": "SaveImage",
"inputs": {
"images": ["7", 0],
"filename_prefix": "voice-creator-v3/profile"
}
},
"6": {
"class_type": "FluxKontextImageScale",
"inputs": {
"image": ["4", 0]
}
},
"10": {
"class_type": "TextEncodeQwenImageEditPlus",
"inputs": {
"clip": ["2", 0],
"vae": ["3", 0],
"image1": ["6", 0],
"image2": ["61", 0],
"prompt": ""
}
},
"11": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": 512,
"height": 1024,
"batch_size": 1
}
},
"12": {
"class_type": "KSampler",
"inputs": {
"model": ["1", 0],
"seed": 0,
"steps": 20,
"cfg": 1.0,
"sampler_name": "euler",
"scheduler": "simple",
"positive": ["10", 0],
"negative": ["10", 0],
"latent_image": ["11", 0],
"denoise": 1.0
}
},
"13": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["12", 0],
"vae": ["3", 0]
}
},
"14": {
"class_type": "TextEncodeQwenImageEditPlus",
"inputs": {
"clip": ["2", 0],
"vae": ["3", 0],
"image1": ["6", 0],
"image2": ["63", 0],
"prompt": ""
}
},
"15": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": 512,
"height": 1024,
"batch_size": 1
}
},
"16": {
"class_type": "KSampler",
"inputs": {
"model": ["1", 0],
"seed": 0,
"steps": 20,
"cfg": 1.0,
"sampler_name": "euler",
"scheduler": "simple",
"positive": ["14", 0],
"negative": ["14", 0],
"latent_image": ["15", 0],
"denoise": 1.0
}
},
"17": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["16", 0],
"vae": ["3", 0]
}
},
"18": {
"class_type": "TextEncodeQwenImageEditPlus",
"inputs": {
"clip": ["2", 0],
"vae": ["3", 0],
"image1": ["6", 0],
"image2": ["65", 0],
"prompt": ""
}
},
"19": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": 512,
"height": 1024,
"batch_size": 1
}
},
"40": {
"class_type": "KSampler",
"inputs": {
"model": ["1", 0],
"seed": 0,
"steps": 20,
"cfg": 1.0,
"sampler_name": "euler",
"scheduler": "simple",
"positive": ["18", 0],
"negative": ["18", 0],
"latent_image": ["19", 0],
"denoise": 1.0
}
},
"41": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["40", 0],
"vae": ["3", 0]
}
},
"20": {
"class_type": "UNETLoader",
"inputs": {
"unet_name": "qwen-image-2512-fp8.safetensors",
"weight_dtype": "default"
}
},
"21": {
"class_type": "LoraLoaderModelOnly",
"inputs": {
"model": ["20", 0],
"lora_name": "Qwen-Image-Lightning-4steps-V1.0-bf16.safetensors",
"strength_model": 1.0
}
},
"22": {
"class_type": "ModelSamplingAuraFlow",
"inputs": {
"model": ["21", 0],
"shift": 3.1
}
},
"23": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": ["2", 0],
"text": ""
}
},
"24": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": ["2", 0],
"text": "low quality, malformed object, duplicate object, fragment, extra item, person, hand, modern object, text, label, logo, watermark"
}
},
"25": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": 512,
"height": 512,
"batch_size": 1
}
},
"26": {
"class_type": "KSampler",
"inputs": {
"model": ["22", 0],
"seed": 0,
"steps": 4,
"cfg": 1.0,
"sampler_name": "euler",
"scheduler": "simple",
"positive": ["23", 0],
"negative": ["24", 0],
"latent_image": ["25", 0],
"denoise": 1.0
}
},
"27": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["26", 0],
"vae": ["3", 0]
}
},
"28": {
"class_type": "ImageScale",
"inputs": {
"image": ["13", 0],
"upscale_method": "lanczos",
"width": 512,
"height": 1024,
"crop": "disabled"
}
},
"29": {
"class_type": "ImageScale",
"inputs": {
"image": ["17", 0],
"upscale_method": "lanczos",
"width": 512,
"height": 1024,
"crop": "disabled"
}
},
"30": {
"class_type": "ImageScale",
"inputs": {
"image": ["41", 0],
"upscale_method": "lanczos",
"width": 512,
"height": 1024,
"crop": "disabled"
}
},
"31": {
"class_type": "ImageStitch",
"inputs": {
"image1": ["28", 0],
"image2": ["29", 0],
"direction": "right",
"match_image_size": true,
"spacing_width": 0,
"spacing_color": "white"
}
},
"32": {
"class_type": "ImageStitch",
"inputs": {
"image1": ["31", 0],
"image2": ["30", 0],
"direction": "right",
"match_image_size": true,
"spacing_width": 0,
"spacing_color": "white"
}
},
"33": {
"class_type": "ImageCrop",
"inputs": {
"image": ["4", 0],
"width": 768,
"height": 512,
"x": 128,
"y": 0
}
},
"34": {
"class_type": "ImageScale",
"inputs": {
"image": ["33", 0],
"upscale_method": "lanczos",
"width": 768,
"height": 512,
"crop": "disabled"
}
},
"35": {
"class_type": "ImageScale",
"inputs": {
"image": ["27", 0],
"upscale_method": "lanczos",
"width": 768,
"height": 512,
"crop": "disabled"
}
},
"36": {
"class_type": "ImageStitch",
"inputs": {
"image1": ["34", 0],
"image2": ["35", 0],
"direction": "right",
"match_image_size": true,
"spacing_width": 0,
"spacing_color": "white"
}
},
"37": {
"class_type": "ImageStitch",
"inputs": {
"image1": ["32", 0],
"image2": ["36", 0],
"direction": "down",
"match_image_size": false,
"spacing_width": 0,
"spacing_color": "white"
}
},
"front_save": {
"class_type": "SaveImage",
"inputs": {
"images": ["13", 0],
"filename_prefix": "voice-creator-v4/front"
}
},
"side_save": {
"class_type": "SaveImage",
"inputs": {
"images": ["17", 0],
"filename_prefix": "voice-creator-v4/side"
}
},
"back_save": {
"class_type": "SaveImage",
"inputs": {
"images": ["41", 0],
"filename_prefix": "voice-creator-v4/back"
}
},
"42": {
"class_type": "TextEncodeQwenImageEditPlus",
"inputs": {
"clip": ["2", 0],
"vae": ["3", 0],
"image1": ["6", 0],
"prompt": ""
}
},
"43": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": 768,
"height": 512,
"batch_size": 1
}
},
"44": {
"class_type": "KSampler",
"inputs": {
"model": ["1", 0],
"seed": 0,
"steps": 20,
"cfg": 1.0,
"sampler_name": "euler",
"scheduler": "simple",
"positive": ["42", 0],
"negative": ["42", 0],
"latent_image": ["43", 0],
"denoise": 1.0
}
},
"45": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["44", 0],
"vae": ["3", 0]
}
},
"scene_save": {
"class_type": "SaveImage",
"inputs": {
"images": ["45", 0],
"filename_prefix": "voice-creator-v4/scene"
}
},
"prop1_save": {
"class_type": "SaveImage",
"inputs": {
"images": ["27", 0],
"filename_prefix": "voice-creator-v4/prop-1"
}
},
"50": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": ["2", 0],
"text": ""
}
},
"51": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": 512,
"height": 512,
"batch_size": 1
}
},
"52": {
"class_type": "KSampler",
"inputs": {
"model": ["22", 0],
"seed": 0,
"steps": 4,
"cfg": 1.0,
"sampler_name": "euler",
"scheduler": "simple",
"positive": ["50", 0],
"negative": ["24", 0],
"latent_image": ["51", 0],
"denoise": 1.0
}
},
"53": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["52", 0],
"vae": ["3", 0]
}
},
"prop2_save": {
"class_type": "SaveImage",
"inputs": {
"images": ["53", 0],
"filename_prefix": "voice-creator-v4/prop-2"
}
},
"54": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": ["2", 0],
"text": ""
}
},
"55": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": 512,
"height": 512,
"batch_size": 1
}
},
"56": {
"class_type": "KSampler",
"inputs": {
"model": ["22", 0],
"seed": 0,
"steps": 4,
"cfg": 1.0,
"sampler_name": "euler",
"scheduler": "simple",
"positive": ["54", 0],
"negative": ["24", 0],
"latent_image": ["55", 0],
"denoise": 1.0
}
},
"57": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["56", 0],
"vae": ["3", 0]
}
},
"prop3_save": {
"class_type": "SaveImage",
"inputs": {
"images": ["57", 0],
"filename_prefix": "voice-creator-v4/prop-3"
}
},
"60": {
"class_type": "LoadImage",
"inputs": {
"image": "voice_creator_pose_front.png"
}
},
"61": {
"class_type": "FluxKontextImageScale",
"inputs": {
"image": ["60", 0]
}
},
"62": {
"class_type": "LoadImage",
"inputs": {
"image": "voice_creator_pose_side.png"
}
},
"63": {
"class_type": "FluxKontextImageScale",
"inputs": {
"image": ["62", 0]
}
},
"64": {
"class_type": "LoadImage",
"inputs": {
"image": "voice_creator_pose_back.png"
}
},
"65": {
"class_type": "FluxKontextImageScale",
"inputs": {
"image": ["64", 0]
}
},
"66": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": ["2", 0],
"text": ""
}
},
"67": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": ["2", 0],
"text": "low quality, illustration, painting, cartoon, anime, glossy 3D render, modern clothing, hat, headwear, repeated front view, three-quarter view, cropped head, cropped feet, duplicate figure, extra figure, extra limbs, prop, text, label, logo, watermark"
}
},
"68": {
"class_type": "KSampler",
"inputs": {
"model": ["22", 0],
"seed": 0,
"steps": 4,
"cfg": 1.0,
"sampler_name": "euler",
"scheduler": "simple",
"positive": ["66", 0],
"negative": ["67", 0],
"latent_image": ["69", 0],
"denoise": 1.0
}
},
"69": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": 1536,
"height": 1024,
"batch_size": 1
}
},
"turnaround_decode": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["68", 0],
"vae": ["3", 0]
}
},
"turnaround_save": {
"class_type": "SaveImage",
"inputs": {
"images": ["turnaround_decode", 0],
"filename_prefix": "voice-creator-v5/turnaround"
}
},
"70": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": ["2", 0],
"text": ""
}
},
"71": {
"class_type": "CLIPTextEncode",
"inputs": {
"clip": ["2", 0],
"text": "low quality, catalog pose, studio portrait, character sheet, modern clothing, hat, headwear, cropped head, cropped hands, duplicate main character, extra limbs, repeated prop, text, label, logo, watermark"
}
},
"72": {
"class_type": "KSampler",
"inputs": {
"model": ["22", 0],
"seed": 0,
"steps": 4,
"cfg": 1.0,
"sampler_name": "euler",
"scheduler": "simple",
"positive": ["70", 0],
"negative": ["71", 0],
"latent_image": ["73", 0],
"denoise": 1.0
}
},
"73": {
"class_type": "EmptySD3LatentImage",
"inputs": {
"width": 768,
"height": 512,
"batch_size": 1
}
},
"scene_t2i_decode": {
"class_type": "VAEDecode",
"inputs": {
"samples": ["72", 0],
"vae": ["3", 0]
}
},
"scene_t2i_save": {
"class_type": "SaveImage",
"inputs": {
"images": ["scene_t2i_decode", 0],
"filename_prefix": "voice-creator-v5/scene"
}
}
}