{ "config": {}, "extra": { "VHS_KeepIntermediate": true, "VHS_MetadataImage": true, "VHS_latentpreview": false, "VHS_latentpreviewrate": 0, "ds": { "offset": [ 1276.3348183999904, 1316.4990758496092 ], "scale": 0.46650738020973354 }, "frontendVersion": "1.45.15", "linearData": { "inputs": [ [ "94", "tags", { "height": 115 } ], [ "128", "value" ], [ "129", "value" ], [ "94", "keyscale" ], [ "112", "value", { "height": 121 } ], [ "115", "sampling_mode.seed" ], [ "117", "value" ] ], "outputs": [ "119", "111" ] }, "linearMode": true, "workflowRendererVersion": "LG" }, "groups": [ { "bounding": [ -210, -950, 440, 640 ], "color": "#3f789e", "flags": {}, "id": 1, "title": "Model" }, { "bounding": [ 260, -950, 640, 960 ], "color": "#3f789e", "flags": {}, "id": 3, "title": "Prompt" }, { "bounding": [ -2720, -950, 2450, 1142 ], "color": "#88537f", "flags": {}, "id": 4, "title": "Lyrics Generation (auto + BPM/duration aware)" } ], "id": "88ac5dad-efd7-40bb-84fe-fbaefdee1fa9", "last_link_id": 288, "last_node_id": 132, "links": [ [ 119, 47, 0, 3, 2, "CONDITIONING" ], [ 175, 78, 0, 3, 0, "MODEL" ], [ 249, 98, 0, 3, 3, "LATENT" ], [ 254, 94, 0, 3, 1, "CONDITIONING" ], [ 255, 94, 0, 47, 0, "CONDITIONING" ], [ 256, 3, 0, 18, 0, "LATENT" ], [ 260, 104, 0, 78, 0, "MODEL" ], [ 261, 105, 0, 94, 0, "CLIP" ], [ 262, 106, 0, 18, 1, "VAE" ], [ 266, 18, 0, 111, 0, "AUDIO" ], [ 267, 112, 0, 114, 2, "STRING" ], [ 268, 113, 0, 115, 0, "CLIP" ], [ 269, 114, 0, 131, 0, "STRING" ], [ 270, 115, 0, 116, 1, "STRING" ], [ 271, 117, 0, 116, 0, "STRING" ], [ 273, 116, 0, 94, 2, "STRING" ], [ 275, 117, 0, 121, 0, "STRING" ], [ 276, 121, 0, 116, 2, "BOOLEAN" ], [ 278, 116, 0, 119, 0, "STRING" ], [ 280, 128, 0, 94, 5, "FLOAT" ], [ 281, 128, 0, 98, 0, "FLOAT" ], [ 282, 129, 0, 94, 4, "INT" ], [ 283, 129, 0, 127, 0, "INT" ], [ 284, 128, 0, 130, 0, "FLOAT" ], [ 285, 131, 0, 132, 0, "STRING" ], [ 286, 132, 0, 115, 4, "STRING" ], [ 287, 130, 0, 131, 2, "STRING" ], [ 288, 127, 0, 132, 2, "STRING" ] ], "nodes": [ { "flags": {}, "id": 104, "inputs": [ { "link": null, "localized_name": "unet_name", "name": "unet_name", "type": "COMBO", "widget": { "name": "unet_name" } }, { "link": null, "localized_name": "weight_dtype", "name": "weight_dtype", "type": "COMBO", "widget": { "name": "weight_dtype" } } ], "mode": 0, "order": 0, "outputs": [ { "links": [ 260 ], "localized_name": "MODEL", "name": "MODEL", "type": "MODEL" } ], "pos": [ -190, -880 ], "properties": { "Node name for S&R": "UNETLoader", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "models": [ { "directory": "diffusion_models", "name": "acestep_v1.5_xl_turbo_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/diffusion_models/acestep_v1.5_xl_turbo_bf16.safetensors" } ], "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.11.1" }, "size": [ 380, 120 ], "type": "UNETLoader", "widgets_values": [ "acestep_v1.5_xl_turbo_bf16.safetensors", "default" ] }, { "flags": {}, "id": 106, "inputs": [ { "link": null, "localized_name": "vae_name", "name": "vae_name", "type": "COMBO", "widget": { "name": "vae_name" } } ], "mode": 0, "order": 1, "outputs": [ { "links": [ 262 ], "localized_name": "VAE", "name": "VAE", "type": "VAE" } ], "pos": [ -190, -440 ], "properties": { "Node name for S&R": "VAELoader", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "models": [ { "directory": "vae", "name": "ace_1.5_vae.safetensors", "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/vae/ace_1.5_vae.safetensors" } ], "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.11.1" }, "size": [ 380, 110 ], "type": "VAELoader", "widgets_values": [ "ace_1.5_vae.safetensors" ] }, { "flags": { "collapsed": true }, "id": 98, "inputs": [ { "link": 281, "localized_name": "seconds", "name": "seconds", "type": "FLOAT", "widget": { "name": "seconds" } }, { "link": null, "localized_name": "batch_size", "name": "batch_size", "type": "INT", "widget": { "name": "batch_size" } } ], "mode": 0, "order": 12, "outputs": [ { "links": [ 249 ], "localized_name": "LATENT", "name": "LATENT", "type": "LATENT" } ], "pos": [ 280, -40 ], "properties": { "Node name for S&R": "EmptyAceStep1.5LatentAudio", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.11.1" }, "size": [ 271, 8 ], "type": "EmptyAceStep1.5LatentAudio", "widgets_values": [ 120, 1 ] }, { "flags": { "collapsed": true }, "id": 47, "inputs": [ { "link": 255, "localized_name": "conditioning", "name": "conditioning", "type": "CONDITIONING" } ], "mode": 0, "order": 21, "outputs": [ { "links": [ 119 ], "localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING" } ], "pos": [ 640, -40 ], "properties": { "Node name for S&R": "ConditioningZeroOut", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.11.1" }, "size": [ 225, 8 ], "type": "ConditioningZeroOut", "widgets_values": [] }, { "flags": {}, "id": 3, "inputs": [ { "link": 175, "localized_name": "model", "name": "model", "type": "MODEL" }, { "link": 254, "localized_name": "positive", "name": "positive", "type": "CONDITIONING" }, { "link": 119, "localized_name": "negative", "name": "negative", "type": "CONDITIONING" }, { "link": 249, "localized_name": "latent_image", "name": "latent_image", "type": "LATENT" }, { "link": null, "localized_name": "seed", "name": "seed", "type": "INT", "widget": { "name": "seed" } }, { "link": null, "localized_name": "steps", "name": "steps", "type": "INT", "widget": { "name": "steps" } }, { "link": null, "localized_name": "cfg", "name": "cfg", "type": "FLOAT", "widget": { "name": "cfg" } }, { "link": null, "localized_name": "sampler_name", "name": "sampler_name", "type": "COMBO", "widget": { "name": "sampler_name" } }, { "link": null, "localized_name": "scheduler", "name": "scheduler", "type": "COMBO", "widget": { "name": "scheduler" } }, { "link": null, "localized_name": "denoise", "name": "denoise", "type": "FLOAT", "widget": { "name": "denoise" } } ], "mode": 0, "order": 22, "outputs": [ { "links": [ 256 ], "localized_name": "LATENT", "name": "LATENT", "slot_index": 0, "type": "LATENT" } ], "pos": [ 930, -670 ], "properties": { "Node name for S&R": "KSampler", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.11.1" }, "size": [ 330, 376 ], "type": "KSampler", "widgets_values": [ 0, "fixed", 12, 1, "euler", "simple", 1 ] }, { "flags": {}, "id": 78, "inputs": [ { "link": 260, "localized_name": "model", "name": "model", "type": "MODEL" }, { "link": null, "localized_name": "shift", "name": "shift", "type": "FLOAT", "widget": { "name": "shift" } } ], "mode": 0, "order": 9, "outputs": [ { "links": [ 175 ], "localized_name": "MODEL", "name": "MODEL", "type": "MODEL" } ], "pos": [ 930, -860 ], "properties": { "Node name for S&R": "ModelSamplingAuraFlow", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.11.1" }, "size": [ 330, 80 ], "type": "ModelSamplingAuraFlow", "widgets_values": [ 3 ] }, { "flags": {}, "id": 18, "inputs": [ { "link": 256, "localized_name": "samples", "name": "samples", "type": "LATENT" }, { "link": 262, "localized_name": "vae", "name": "vae", "type": "VAE" } ], "mode": 0, "order": 23, "outputs": [ { "links": [ 266 ], "localized_name": "AUDIO", "name": "AUDIO", "type": "AUDIO" } ], "pos": [ 1320, -860 ], "properties": { "Node name for S&R": "VAEDecodeAudio", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.11.1" }, "size": [ 230, 100 ], "type": "VAEDecodeAudio", "widgets_values": [] }, { "flags": {}, "id": 105, "inputs": [ { "link": null, "localized_name": "clip_name1", "name": "clip_name1", "type": "COMBO", "widget": { "name": "clip_name1" } }, { "link": null, "localized_name": "clip_name2", "name": "clip_name2", "type": "COMBO", "widget": { "name": "clip_name2" } }, { "link": null, "localized_name": "type", "name": "type", "type": "COMBO", "widget": { "name": "type" } }, { "link": null, "localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": { "name": "device" } } ], "mode": 0, "order": 2, "outputs": [ { "links": [ 261 ], "localized_name": "CLIP", "name": "CLIP", "type": "CLIP" } ], "pos": [ -190, -690 ], "properties": { "Node name for S&R": "DualCLIPLoader", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "models": [ { "directory": "text_encoders", "name": "qwen_0.6b_ace15.safetensors", "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_0.6b_ace15.safetensors" }, { "directory": "text_encoders", "name": "qwen_4b_ace15.safetensors", "url": "https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/split_files/text_encoders/qwen_4b_ace15.safetensors" } ], "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.11.1" }, "size": [ 380, 180 ], "type": "DualCLIPLoader", "widgets_values": [ "qwen_0.6b_ace15.safetensors", "qwen_4b_ace15.safetensors", "ace", "default" ] }, { "flags": {}, "id": 94, "inputs": [ { "link": 261, "localized_name": "clip", "name": "clip", "type": "CLIP" }, { "label": "Song Tags", "link": null, "localized_name": "tags", "name": "tags", "type": "STRING", "widget": { "name": "tags" } }, { "link": 273, "localized_name": "lyrics", "name": "lyrics", "type": "STRING", "widget": { "name": "lyrics" } }, { "label": "Song Seed (change to generate new song)", "link": null, "localized_name": "seed", "name": "seed", "type": "INT", "widget": { "name": "seed" } }, { "link": 282, "localized_name": "bpm", "name": "bpm", "type": "INT", "widget": { "name": "bpm" } }, { "link": 280, "localized_name": "duration", "name": "duration", "type": "FLOAT", "widget": { "name": "duration" } }, { "link": null, "localized_name": "timesignature", "name": "timesignature", "type": "COMBO", "widget": { "name": "timesignature" } }, { "link": null, "localized_name": "language", "name": "language", "type": "COMBO", "widget": { "name": "language" } }, { "label": "Keyscale", "link": null, "localized_name": "keyscale", "name": "keyscale", "type": "COMBO", "widget": { "name": "keyscale" } }, { "link": null, "localized_name": "generate_audio_codes", "name": "generate_audio_codes", "type": "BOOLEAN", "widget": { "name": "generate_audio_codes" } }, { "link": null, "localized_name": "cfg_scale", "name": "cfg_scale", "type": "FLOAT", "widget": { "name": "cfg_scale" } }, { "link": null, "localized_name": "temperature", "name": "temperature", "type": "FLOAT", "widget": { "name": "temperature" } }, { "link": null, "localized_name": "top_p", "name": "top_p", "type": "FLOAT", "widget": { "name": "top_p" } }, { "link": null, "localized_name": "top_k", "name": "top_k", "type": "INT", "widget": { "name": "top_k" } }, { "link": null, "localized_name": "min_p", "name": "min_p", "type": "FLOAT", "widget": { "name": "min_p" } } ], "mode": 0, "order": 19, "outputs": [ { "links": [ 254, 255 ], "localized_name": "CONDITIONING", "name": "CONDITIONING", "type": "CONDITIONING" } ], "pos": [ 290, -860 ], "properties": { "Node name for S&R": "TextEncodeAceStepAudio1.5", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.11.1" }, "size": [ 570, 700 ], "type": "TextEncodeAceStepAudio1.5", "widgets_values": [ "Lo-fi hip-hop chill track with mellow electric piano, soft vinyl crackle, subtle synth pads, low-pass filtered drums, percussion loops, and soft plucked bass for a relaxed, dreamy vibe.", "", 1103026267678031, "randomize", 95, 120, "4", "en", "E minor", true, 2, 0.85, 0.9, 0, 0 ] }, { "flags": {}, "id": 111, "inputs": [ { "link": 266, "localized_name": "audio", "name": "audio", "type": "AUDIO" }, { "link": null, "localized_name": "filename_prefix", "name": "filename_prefix", "type": "STRING", "widget": { "name": "filename_prefix" } }, { "link": null, "localized_name": "format", "name": "format", "type": "COMFY_DYNAMICCOMBO_V3", "widget": { "name": "format" } }, { "link": null, "localized_name": "format.quality", "name": "format.quality", "type": "COMBO", "widget": { "name": "format.quality" } }, { "link": null, "localized_name": "audioUI", "name": "audioUI", "type": "AUDIO_UI", "widget": { "name": "audioUI" } } ], "mode": 0, "order": 24, "outputs": [ { "links": null, "localized_name": "audio", "name": "audio", "type": "AUDIO" } ], "pos": [ 1320, -670 ], "properties": { "Node name for S&R": "SaveAudioAdvanced" }, "size": [ 710, 216 ], "type": "SaveAudioAdvanced", "widgets_values": [ "audio/ACE_Step1.5_xl_turbo", "mp3", "V0" ] }, { "flags": {}, "id": 112, "inputs": [ { "label": "Song Topic (guides lyric auto-generation)", "link": null, "localized_name": "value", "name": "value", "type": "STRING", "widget": { "name": "value" } } ], "mode": 0, "order": 3, "outputs": [ { "links": [ 267 ], "localized_name": "STRING", "name": "STRING", "type": "STRING" } ], "pos": [ -2150, -650 ], "properties": { "Node name for S&R": "PrimitiveStringMultiline" }, "size": [ 420, 220 ], "title": "User: song topic (USER_INPUT)", "type": "PrimitiveStringMultiline", "widgets_values": [ "An upbeat electronic anthem about building workflows in ComfyUI — connecting nodes late at night and watching the render come through." ] }, { "flags": {}, "id": 113, "inputs": [ { "link": null, "localized_name": "clip_name", "name": "clip_name", "type": "COMBO", "widget": { "name": "clip_name" } }, { "link": null, "localized_name": "type", "name": "type", "type": "COMBO", "widget": { "name": "type" } }, { "link": null, "localized_name": "device", "name": "device", "shape": 7, "type": "COMBO", "widget": { "name": "device" } } ], "mode": 0, "order": 4, "outputs": [ { "links": [ 268 ], "localized_name": "CLIP", "name": "CLIP", "type": "CLIP" } ], "pos": [ -2150, -880 ], "properties": { "Node name for S&R": "CLIPLoader", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "models": [ { "directory": "text_encoders", "name": "qwen3.5_4b_bf16.safetensors", "url": "https://huggingface.co/Comfy-Org/Qwen3.5/resolve/main/text_encoders/qwen3.5_4b_bf16.safetensors" } ], "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.18.1" }, "size": [ 420, 170 ], "title": "CLIP Loader (Qwen LLM for lyrics)", "type": "CLIPLoader", "widgets_values": [ "qwen3.5_4b_bf16.safetensors", "stable_diffusion", "default" ] }, { "flags": {}, "id": 114, "inputs": [ { "link": null, "localized_name": "string", "name": "string", "type": "STRING", "widget": { "name": "string" } }, { "link": null, "localized_name": "find", "name": "find", "type": "STRING", "widget": { "name": "find" } }, { "link": 267, "localized_name": "replace", "name": "replace", "type": "STRING", "widget": { "name": "replace" } } ], "mode": 0, "order": 10, "outputs": [ { "links": [ 269 ], "localized_name": "STRING", "name": "STRING", "type": "STRING" } ], "pos": [ -1690, -870 ], "properties": { "Node name for S&R": "StringReplace" }, "size": [ 490, 470 ], "title": "Lyrics Prompt (fill USER_INPUT)", "type": "StringReplace", "widgets_values": [ "You are a professional songwriter. Write complete, singable lyrics about the topic below.\n\nThe song is about TARGET_DURATION seconds long at TARGET_BPM BPM. Write enough sections to fill that length naturally:\n- around 120-150s: 2 verses + 2 choruses.\n- around 180-240s: also add a bridge.\n- 210s or more: also add a short intro and outro.\nAt slower tempo (under 90 BPM) use fewer words per line; at faster tempo (over 130 BPM) you can fit more, but keep every line easy to sing in one breath.\n\nOutput ONLY the lyrics — no title, no notes, no explanation.\n\nPut each section tag on its own line, e.g. [Intro], [Verse 1], [Chorus], [Verse 2], [Bridge], [Outro].\n\nRules:\n- Blank line between sections.\n- 6-10 syllables per line; keep lines within a section a similar length.\n- Rhyme the verses; give the chorus one short, repeatable hook.\n- Stay with ONE core image or metaphor.\n- Plain, concrete lines a singer can breathe through — no stacked adjectives or vague filler (neon skies, electric hearts, endless dreams).\n\nTopic: USER_INPUT\nLyrics:", "USER_INPUT", "" ] }, { "flags": {}, "id": 131, "inputs": [ { "link": 269, "localized_name": "string", "name": "string", "type": "STRING", "widget": { "name": "string" } }, { "link": null, "localized_name": "find", "name": "find", "type": "STRING", "widget": { "name": "find" } }, { "link": 287, "localized_name": "replace", "name": "replace", "type": "STRING", "widget": { "name": "replace" } } ], "mode": 0, "order": 15, "outputs": [ { "links": [ 285 ], "localized_name": "STRING", "name": "STRING", "type": "STRING" } ], "pos": [ -2150, -370 ], "properties": { "Node name for S&R": "StringReplace" }, "size": [ 420, 252 ], "title": "Inject DURATION (TARGET_DURATION)", "type": "StringReplace", "widgets_values": [ "", "TARGET_DURATION", "" ] }, { "flags": {}, "id": 132, "inputs": [ { "link": 285, "localized_name": "string", "name": "string", "type": "STRING", "widget": { "name": "string" } }, { "link": null, "localized_name": "find", "name": "find", "type": "STRING", "widget": { "name": "find" } }, { "link": 288, "localized_name": "replace", "name": "replace", "type": "STRING", "widget": { "name": "replace" } } ], "mode": 0, "order": 16, "outputs": [ { "links": [ 286 ], "localized_name": "STRING", "name": "STRING", "type": "STRING" } ], "pos": [ -2150, -70 ], "properties": { "Node name for S&R": "StringReplace" }, "size": [ 420, 252 ], "title": "Inject BPM (TARGET_BPM)", "type": "StringReplace", "widgets_values": [ "", "TARGET_BPM", "" ] }, { "flags": {}, "id": 117, "inputs": [ { "label": "Manual Lyrics (leave empty to auto-generate)", "link": null, "localized_name": "value", "name": "value", "type": "STRING", "widget": { "name": "value" } } ], "mode": 0, "order": 5, "outputs": [ { "links": [ 271, 275 ], "localized_name": "STRING", "name": "STRING", "type": "STRING" } ], "pos": [ -1620, -260 ], "properties": { "Node name for S&R": "PrimitiveStringMultiline" }, "size": [ 420, 270 ], "title": "Manual lyrics (leave EMPTY to auto-generate)", "type": "PrimitiveStringMultiline", "widgets_values": [ "" ] }, { "flags": {}, "id": 115, "inputs": [ { "link": 268, "localized_name": "clip", "name": "clip", "type": "CLIP" }, { "link": null, "localized_name": "image", "name": "image", "shape": 7, "type": "IMAGE" }, { "link": null, "localized_name": "video", "name": "video", "shape": 7, "type": "IMAGE" }, { "link": null, "localized_name": "audio", "name": "audio", "shape": 7, "type": "AUDIO" }, { "link": 286, "localized_name": "prompt", "name": "prompt", "type": "STRING", "widget": { "name": "prompt" } }, { "link": null, "localized_name": "max_length", "name": "max_length", "type": "INT", "widget": { "name": "max_length" } }, { "link": null, "localized_name": "sampling_mode", "name": "sampling_mode", "type": "COMFY_DYNAMICCOMBO_V3", "widget": { "name": "sampling_mode" } }, { "link": null, "localized_name": "temperature", "name": "sampling_mode.temperature", "type": "FLOAT", "widget": { "name": "sampling_mode.temperature" } }, { "link": null, "localized_name": "top_k", "name": "sampling_mode.top_k", "type": "INT", "widget": { "name": "sampling_mode.top_k" } }, { "link": null, "localized_name": "top_p", "name": "sampling_mode.top_p", "type": "FLOAT", "widget": { "name": "sampling_mode.top_p" } }, { "link": null, "localized_name": "min_p", "name": "sampling_mode.min_p", "type": "FLOAT", "widget": { "name": "sampling_mode.min_p" } }, { "link": null, "localized_name": "repetition_penalty", "name": "sampling_mode.repetition_penalty", "type": "FLOAT", "widget": { "name": "sampling_mode.repetition_penalty" } }, { "label": "Lyrics Seed (change to generate new lyrics)", "link": null, "localized_name": "seed", "name": "sampling_mode.seed", "type": "INT", "widget": { "name": "sampling_mode.seed" } }, { "link": null, "localized_name": "presence_penalty", "name": "sampling_mode.presence_penalty", "shape": 7, "type": "FLOAT", "widget": { "name": "sampling_mode.presence_penalty" } }, { "link": null, "localized_name": "thinking", "name": "thinking", "shape": 7, "type": "BOOLEAN", "widget": { "name": "thinking" } }, { "link": null, "localized_name": "use_default_template", "name": "use_default_template", "shape": 7, "type": "BOOLEAN", "widget": { "name": "use_default_template" } } ], "mode": 0, "order": 17, "outputs": [ { "links": [ 270 ], "localized_name": "generated_text", "name": "generated_text", "type": "STRING" } ], "pos": [ -1170, -870 ], "properties": { "Node name for S&R": "TextGenerate", "cnr_id": "comfy-core", "enableTabs": false, "hasSecondTab": false, "secondTabOffset": 80, "secondTabText": "Send Back", "secondTabWidth": 65, "tabWidth": 65, "tabXOffset": 10, "ver": "0.18.1" }, "size": [ 430, 532 ], "title": "Qwen TextGenerate (lyrics)", "type": "TextGenerate", "widgets_values": [ "", 512, "on", 0.7, 64, 0.95, 0.05, 1.05, 35146436134, 0, false, true ] }, { "flags": {}, "id": 116, "inputs": [ { "link": 271, "localized_name": "on_false", "name": "on_false", "type": "STRING" }, { "link": 270, "localized_name": "on_true", "name": "on_true", "type": "STRING" }, { "link": 276, "localized_name": "switch", "name": "switch", "type": "BOOLEAN", "widget": { "name": "switch" } } ], "mode": 0, "order": 18, "outputs": [ { "links": [ 273, 278 ], "localized_name": "output", "name": "output", "type": "STRING" } ], "pos": [ -630, -870 ], "properties": { "Node name for S&R": "ComfySwitchNode" }, "size": [ 280, 130 ], "title": "Switch (auto: LLM if manual empty)", "type": "ComfySwitchNode", "widgets_values": [ false ] }, { "flags": { "collapsed": true }, "id": 121, "inputs": [ { "link": 275, "localized_name": "string_a", "name": "string_a", "type": "STRING", "widget": { "name": "string_a" } }, { "link": null, "localized_name": "string_b", "name": "string_b", "type": "STRING", "widget": { "name": "string_b" } }, { "link": null, "localized_name": "mode", "name": "mode", "type": "COMBO", "widget": { "name": "mode" } }, { "link": null, "localized_name": "case_sensitive", "name": "case_sensitive", "type": "BOOLEAN", "widget": { "name": "case_sensitive" } } ], "mode": 0, "order": 11, "outputs": [ { "links": [ 276 ], "localized_name": "BOOLEAN", "name": "BOOLEAN", "type": "BOOLEAN" } ], "pos": [ -1170, -260 ], "properties": { "Node name for S&R": "StringCompare" }, "size": [ 318.53125, 8 ], "title": "Compare Text (manual lyrics == empty)", "type": "StringCompare", "widgets_values": [ "", "", "Equal", true ] }, { "flags": {}, "id": 119, "inputs": [ { "link": 278, "localized_name": "source", "name": "source", "type": "*" } ], "mode": 0, "order": 20, "outputs": [ { "links": null, "localized_name": "STRING", "name": "STRING", "type": "STRING" } ], "pos": [ -720, -680 ], "properties": { "Node name for S&R": "PreviewAny" }, "size": [ 440, 860 ], "title": "Preview Lyrics", "type": "PreviewAny", "widgets_values": [ null, null, null ] }, { "bgcolor": "#000", "color": "#222", "flags": {}, "id": 120, "inputs": [], "mode": 0, "order": 6, "outputs": [], "pos": [ -2710, -880 ], "properties": {}, "size": [ 520, 620 ], "title": "Note: Lyrics branch (BPM + duration aware)", "type": "MarkdownNote", "widgets_values": [ "## Lyrics Generation (BPM + duration aware)\n\nTurns a **short topic** into structured **song lyrics** for ACE-Step, and injects the target **BPM** and **duration** into the songwriter instruction so the LLM writes the right amount of lyrics for the track.\n\n**Flow:** `Topic` + `BPM` + `Duration` → prompt scaffold (`StringReplace` x3, filling `USER_INPUT` / `TARGET_DURATION` / `TARGET_BPM`) → **Qwen `TextGenerate`** → `Switch` → the **lyrics** input of `TextEncodeAceStepAudio1.5`.\n\n`BPM` and `Duration` are the SAME primitives that drive the encoder (`Int (bpm)` + `Float (Duration)`), turned into text by `PreviewAny` — so the words and the audio target the same tempo/length.\n\n**Auto mode:** `Compare Text` checks whether the **manual lyrics** box is empty. Empty → use the LLM lyrics; typed → use your words verbatim.\n\n## Model (text_encoders)\n\n- qwen3.5_4b_bf16.safetensors (LLM for lyrics — confirm the 4B file/URL exists in your setup)\n\nStore in `ComfyUI/models/text_encoders/`." ] }, { "flags": { "collapsed": true }, "id": 127, "inputs": [ { "link": 283, "localized_name": "source", "name": "source", "type": "*" } ], "mode": 0, "order": 14, "outputs": [ { "links": [ 288 ], "localized_name": "STRING", "name": "STRING", "type": "STRING" } ], "pos": [ -2410, 150 ], "properties": { "Node name for S&R": "PreviewAny" }, "size": [ 225, 8 ], "title": "bpm to string", "type": "PreviewAny", "widgets_values": [ null, null, null ] }, { "flags": {}, "id": 128, "inputs": [ { "label": "Duration (seconds)", "link": null, "localized_name": "value", "name": "value", "type": "FLOAT", "widget": { "name": "value" } } ], "mode": 0, "order": 7, "outputs": [ { "links": [ 280, 281, 284 ], "localized_name": "FLOAT", "name": "FLOAT", "type": "FLOAT" } ], "pos": [ -2710, -180 ], "properties": { "Node name for S&R": "PrimitiveFloat" }, "size": [ 270, 80 ], "title": "Float (Duration)", "type": "PrimitiveFloat", "widgets_values": [ 120 ] }, { "flags": {}, "id": 129, "inputs": [ { "label": "BPM", "link": null, "localized_name": "value", "name": "value", "type": "INT", "widget": { "name": "value" } } ], "mode": 0, "order": 8, "outputs": [ { "links": [ 282, 283 ], "localized_name": "INT", "name": "INT", "type": "INT" } ], "pos": [ -2710, 80 ], "properties": { "Node name for S&R": "PrimitiveInt" }, "size": [ 270, 90 ], "title": "Int (bpm)", "type": "PrimitiveInt", "widgets_values": [ 90, "fixed" ] }, { "flags": { "collapsed": true }, "id": 130, "inputs": [ { "link": 284, "localized_name": "source", "name": "source", "type": "*" } ], "mode": 0, "order": 13, "outputs": [ { "links": [ 287 ], "localized_name": "STRING", "name": "STRING", "type": "STRING" } ], "pos": [ -2410, -150 ], "properties": { "Node name for S&R": "PreviewAny" }, "size": [ 225, 8 ], "title": "duration to string", "type": "PreviewAny", "widgets_values": [ null, null, null ] } ], "revision": 0, "version": 0.4 }