diff --git a/examples/ace1.5/audio_ace_step_1_5_cover.json b/examples/ace1.5/audio_ace_step_1_5_cover.json index 4b9c87e..5a4f28b 100644 --- a/examples/ace1.5/audio_ace_step_1_5_cover.json +++ b/examples/ace1.5/audio_ace_step_1_5_cover.json @@ -1 +1,1219 @@ -{"id":"5053cd4b-bb11-4361-b515-8844ef227a1c","revision":0,"last_node_id":29,"last_link_id":35,"nodes":[{"id":10,"type":"Knob","pos":[3180.335422078192,529.3368769156402],"size":[270,122],"flags":{},"order":17,"mode":0,"inputs":[{"localized_name":"audio","name":"audio","type":"AUDIO","link":10},{"localized_name":"knob","name":"knob","type":"FLOAT","widget":{"name":"knob"},"link":null},{"localized_name":"other_knob","name":"other_knob","type":"FLOAT","widget":{"name":"other_knob"},"link":null}],"outputs":[{"localized_name":"AUDIO","name":"AUDIO","type":"AUDIO","links":[34]}],"properties":{"cnr_id":"comfyui_ryanontheinside","ver":"951b1318f8958bfc441c0bcbbf2fc0695e1d9278","Node name for S&R":"Knob"},"widgets_values":[0.2,0.05]},{"id":12,"type":"PrimitiveNode","pos":[551.3403829650877,319.3290474243163],"size":[278,82],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"INT","type":"INT","widget":{"name":"duration"},"links":[17]}],"title":"Song Duration","properties":{"Run widget replace on values":false},"widgets_values":[40,"fixed"]},{"id":13,"type":"ConditioningZeroOut","pos":[1180.3403829650877,579.3290474243163],"size":[204.134765625,26],"flags":{},"order":13,"mode":0,"inputs":[{"localized_name":"conditioning","name":"conditioning","type":"CONDITIONING","link":11}],"outputs":[{"localized_name":"CONDITIONING","name":"CONDITIONING","type":"CONDITIONING","links":[21]}],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"ConditioningZeroOut"},"widgets_values":[]},{"id":14,"type":"VAEEncodeAudio","pos":[1218.3403829650877,711.3290474243163],"size":[210,46],"flags":{},"order":7,"mode":0,"inputs":[{"localized_name":"audio","name":"audio","type":"AUDIO","link":12},{"localized_name":"vae","name":"vae","type":"VAE","link":13}],"outputs":[{"localized_name":"LATENT","name":"LATENT","type":"LATENT","links":[22,29]}],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"VAEEncodeAudio"},"widgets_values":[]},{"id":15,"type":"CheckpointLoaderSimple","pos":[463.34038296508766,113.32904742431629],"size":[428,98],"flags":{},"order":2,"mode":0,"inputs":[{"localized_name":"ckpt_name","name":"ckpt_name","type":"COMBO","widget":{"name":"ckpt_name"},"link":null}],"outputs":[{"localized_name":"MODEL","name":"MODEL","type":"MODEL","links":[24]},{"localized_name":"CLIP","name":"CLIP","type":"CLIP","links":[15]},{"localized_name":"VAE","name":"VAE","type":"VAE","links":[13,32]}],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"CheckpointLoaderSimple"},"widgets_values":["ace_step_1.5_turbo_aio.safetensors"]},{"id":16,"type":"VHS_LoadAudioUpload","pos":[259.34038296508766,484.3290474243163],"size":[252.0078125,204],"flags":{},"order":3,"mode":0,"inputs":[{"localized_name":"audio","name":"audio","type":"COMBO","widget":{"name":"audio"},"link":null},{"localized_name":"start_time","name":"start_time","shape":7,"type":"FLOAT","widget":{"name":"start_time"},"link":null},{"localized_name":"duration","name":"duration","shape":7,"type":"FLOAT","widget":{"name":"duration"},"link":null}],"outputs":[{"localized_name":"audio","name":"audio","type":"AUDIO","links":[12,14,35]},{"localized_name":"duration","name":"duration","type":"FLOAT","links":null}],"properties":{"cnr_id":"comfyui-videohelpersuite","ver":"1.7.7","Node name for S&R":"VHS_LoadAudioUpload"},"widgets_values":{"audio":"Vesuvius_v2_edit.wav","start_time":0,"duration":60,"audiopreview":{"params":{"filename":"Vesuvius_v2_edit.wav","type":"input","start_time":0,"duration":60}}}},{"id":17,"type":"AudioInfo","pos":[561.3403829650877,474.3290474243163],"size":[270,378],"flags":{},"order":8,"mode":0,"inputs":[{"localized_name":"audio","name":"audio","type":"AUDIO","link":14},{"localized_name":"frame_rate","name":"frame_rate","type":"FLOAT","widget":{"name":"frame_rate"},"link":null}],"outputs":[{"localized_name":"total_frames","name":"total_frames","type":"INT","links":null},{"localized_name":"frames_per_beat","name":"frames_per_beat","type":"INT","links":null},{"localized_name":"frames_per_bar","name":"frames_per_bar","type":"INT","links":null},{"localized_name":"frames_per_quarter","name":"frames_per_quarter","type":"INT","links":null},{"localized_name":"frames_per_eighth","name":"frames_per_eighth","type":"INT","links":null},{"localized_name":"audio_duration","name":"audio_duration","type":"FLOAT","links":null},{"localized_name":"beats_per_second","name":"beats_per_second","type":"FLOAT","links":null},{"localized_name":"detected_bpm","name":"detected_bpm","type":"FLOAT","links":[]},{"localized_name":"detected_bpm_rounded","name":"detected_bpm_rounded","type":"INT","links":[16]},{"localized_name":"sample_rate","name":"sample_rate","type":"INT","links":null},{"localized_name":"num_channels","name":"num_channels","type":"INT","links":null},{"localized_name":"num_samples","name":"num_samples","type":"INT","links":null},{"localized_name":"max_amplitude","name":"max_amplitude","type":"FLOAT","links":null},{"localized_name":"mean_amplitude","name":"mean_amplitude","type":"FLOAT","links":null},{"localized_name":"rms_amplitude","name":"rms_amplitude","type":"FLOAT","links":null},{"localized_name":"bit_depth","name":"bit_depth","type":"STRING","links":null},{"localized_name":"detected_key","name":"detected_key","type":"COMBO","links":[18]}],"properties":{"cnr_id":"comfyui_ryanontheinside","ver":"418dd269462f0f08096ae5ab899f991500f3a44c","Node name for S&R":"AudioInfo"},"widgets_values":[30]},{"id":19,"type":"ACEStep15NativeCoverGuider","pos":[2120.660994667053,294.4027658107756],"size":[359,146],"flags":{},"order":14,"mode":0,"inputs":[{"localized_name":"model","name":"model","type":"MODEL","link":19},{"localized_name":"positive","name":"positive","type":"CONDITIONING","link":20},{"localized_name":"negative","name":"negative","type":"CONDITIONING","link":21},{"localized_name":"source_latents","name":"source_latents","type":"LATENT","link":22},{"localized_name":"semantic_hints","name":"semantic_hints","shape":7,"type":"SEMANTIC_HINTS","link":null},{"localized_name":"cfg","name":"cfg","type":"FLOAT","widget":{"name":"cfg"},"link":null}],"outputs":[{"localized_name":"GUIDER","name":"GUIDER","type":"GUIDER","links":[26]}],"properties":{"cnr_id":"comfyui_ryanontheinside","ver":"418dd269462f0f08096ae5ab899f991500f3a44c","Node name for S&R":"ACEStep15NativeCoverGuider"},"widgets_values":[1]},{"id":20,"type":"KSamplerSelect","pos":[2160.660994667053,494.4027658107756],"size":[315,58],"flags":{},"order":4,"mode":0,"inputs":[{"localized_name":"sampler_name","name":"sampler_name","type":"COMBO","widget":{"name":"sampler_name"},"link":null}],"outputs":[{"localized_name":"SAMPLER","name":"SAMPLER","type":"SAMPLER","links":[27]}],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"KSamplerSelect"},"widgets_values":["euler"]},{"id":21,"type":"BasicScheduler","pos":[2180.660994667053,674.4027658107756],"size":[270,106],"flags":{},"order":10,"mode":0,"inputs":[{"localized_name":"model","name":"model","type":"MODEL","link":23},{"localized_name":"scheduler","name":"scheduler","type":"COMBO","widget":{"name":"scheduler"},"link":null},{"localized_name":"steps","name":"steps","type":"INT","widget":{"name":"steps"},"link":null},{"localized_name":"denoise","name":"denoise","type":"FLOAT","widget":{"name":"denoise"},"link":null}],"outputs":[{"localized_name":"SIGMAS","name":"SIGMAS","type":"SIGMAS","links":[28]}],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"BasicScheduler"},"widgets_values":["simple",30,1]},{"id":22,"type":"RandomNoise","pos":[2130.660994667053,144.40276581077512],"size":[315,82],"flags":{},"order":5,"mode":0,"inputs":[{"localized_name":"noise_seed","name":"noise_seed","type":"INT","widget":{"name":"noise_seed"},"link":null}],"outputs":[{"localized_name":"NOISE","name":"NOISE","type":"NOISE","links":[25]}],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"RandomNoise"},"widgets_values":[990,"fixed"]},{"id":23,"type":"ModelSamplingAuraFlow","pos":[1693.1675673904415,282.3494657161712],"size":[330,60],"flags":{},"order":6,"mode":0,"inputs":[{"localized_name":"model","name":"model","type":"MODEL","link":24},{"localized_name":"shift","name":"shift","type":"FLOAT","widget":{"name":"shift"},"link":null}],"outputs":[{"localized_name":"MODEL","name":"MODEL","type":"MODEL","links":[19,23]}],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"ModelSamplingAuraFlow"},"widgets_values":[3]},{"id":24,"type":"SamplerCustomAdvanced","pos":[2693.727706092834,376.9360795619962],"size":[212.3638671875,106],"flags":{},"order":15,"mode":0,"inputs":[{"localized_name":"noise","name":"noise","type":"NOISE","link":25},{"localized_name":"guider","name":"guider","type":"GUIDER","link":26},{"localized_name":"sampler","name":"sampler","type":"SAMPLER","link":27},{"localized_name":"sigmas","name":"sigmas","type":"SIGMAS","link":28},{"localized_name":"latent_image","name":"latent_image","type":"LATENT","link":29}],"outputs":[{"localized_name":"output","name":"output","type":"LATENT","links":[]},{"localized_name":"denoised_output","name":"denoised_output","type":"LATENT","links":[31]}],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"SamplerCustomAdvanced"},"widgets_values":[]},{"id":25,"type":"PreviewAudio","pos":[3569.0547222900386,756.6726754379266],"size":[270,88],"flags":{},"order":12,"mode":0,"inputs":[{"localized_name":"audio","name":"audio","type":"AUDIO","link":30},{"localized_name":"audioUI","name":"audioUI","type":"AUDIO_UI","widget":{"name":"audioUI"},"link":null}],"outputs":[],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"PreviewAudio"},"widgets_values":[]},{"id":26,"type":"VAEDecodeAudio","pos":[3032.9211315917964,396.2059891891478],"size":[190,46],"flags":{},"order":16,"mode":0,"inputs":[{"localized_name":"samples","name":"samples","type":"LATENT","link":31},{"localized_name":"vae","name":"vae","type":"VAE","link":32}],"outputs":[{"localized_name":"AUDIO","name":"AUDIO","type":"AUDIO","links":[10,33]}],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"VAEDecodeAudio"},"widgets_values":[]},{"id":27,"type":"SaveAudioMP3","pos":[3288.7883801269527,319.6725495529174],"size":[424.16007385253897,147.58003692626949],"flags":{},"order":18,"mode":0,"inputs":[{"localized_name":"audio","name":"audio","type":"AUDIO","link":33},{"localized_name":"filename_prefix","name":"filename_prefix","type":"STRING","widget":{"name":"filename_prefix"},"link":null},{"localized_name":"quality","name":"quality","type":"COMBO","widget":{"name":"quality"},"link":null},{"localized_name":"audioUI","name":"audioUI","type":"AUDIO_UI","widget":{"name":"audioUI"},"link":null}],"outputs":[],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"SaveAudioMP3"},"widgets_values":["audio/ace_step_cover","V0"]},{"id":28,"type":"PreviewAudio","pos":[3547.6547894287105,559.2726586532592],"size":[270,88],"flags":{},"order":19,"mode":0,"inputs":[{"localized_name":"audio","name":"audio","type":"AUDIO","link":34},{"localized_name":"audioUI","name":"audioUI","type":"AUDIO_UI","widget":{"name":"audioUI"},"link":null}],"outputs":[],"properties":{"cnr_id":"comfy-core","ver":"0.12.2","Node name for S&R":"PreviewAudio"},"widgets_values":[]},{"id":29,"type":"Reroute","pos":[3238.9883465576168,754.4726250839233],"size":[75,26],"flags":{},"order":9,"mode":0,"inputs":[{"name":"","type":"*","link":35}],"outputs":[{"name":"","type":"AUDIO","links":[30]}],"properties":{"showOutputText":false,"horizontal":false}},{"id":18,"type":"ACEStep15TaskTextEncode","pos":[985.3403829650877,149.3290474243163],"size":[400,358],"flags":{},"order":11,"mode":0,"inputs":[{"localized_name":"clip","name":"clip","type":"CLIP","link":15},{"localized_name":"text","name":"text","type":"STRING","widget":{"name":"text"},"link":null},{"localized_name":"task_type","name":"task_type","type":"COMBO","widget":{"name":"task_type"},"link":null},{"localized_name":"track_name","name":"track_name","shape":7,"type":"COMBO","widget":{"name":"track_name"},"link":null},{"localized_name":"lyrics","name":"lyrics","shape":7,"type":"STRING","widget":{"name":"lyrics"},"link":null},{"localized_name":"bpm","name":"bpm","shape":7,"type":"INT","widget":{"name":"bpm"},"link":16},{"localized_name":"duration","name":"duration","shape":7,"type":"INT","widget":{"name":"duration"},"link":17},{"localized_name":"keyscale","name":"keyscale","shape":7,"type":"COMBO","widget":{"name":"keyscale"},"link":18},{"localized_name":"timesignature","name":"timesignature","shape":7,"type":"COMBO","widget":{"name":"timesignature"},"link":null},{"localized_name":"language","name":"language","shape":7,"type":"COMBO","widget":{"name":"language"},"link":null},{"localized_name":"seed","name":"seed","shape":7,"type":"INT","widget":{"name":"seed"},"link":null}],"outputs":[{"localized_name":"conditioning","name":"conditioning","type":"CONDITIONING","links":[11,20]}],"properties":{"cnr_id":"comfyui_ryanontheinside","ver":"418dd269462f0f08096ae5ab899f991500f3a44c","Node name for S&R":"ACEStep15TaskTextEncode"},"widgets_values":["jazz piano cover with swing rhythm","cover","","",120,40,"C major","4","en",0,"fixed"]},{"id":11,"type":"MarkdownNote","pos":[-6.659617034912344,73.32904742431629],"size":[420,360],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[],"properties":{},"widgets_values":["## ACE-Step 1.5 Cover Workflow\n\nAceStep1.5 Cover task\n\nGenerates new content across the entire duration while using the source audio structure as guidance.\n\n**Model:**\n- [ace_step_1.5_turbo_aio.safetensors](https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/checkpoints/ace_step_1.5_turbo_aio.safetensors)\n\n## [gimmi stars on github](https://github.com/ryanontheinside/ComfyUI_RyanOnTheInside)\n\n## [follow me on youtube](https://www.youtube.com/@ryanontheinside)"],"color":"#222","bgcolor":"#000"}],"links":[[10,26,0,10,0,"AUDIO"],[11,18,0,13,0,"CONDITIONING"],[12,16,0,14,0,"AUDIO"],[13,15,2,14,1,"VAE"],[14,16,0,17,0,"AUDIO"],[15,15,1,18,0,"CLIP"],[16,17,8,18,5,"INT"],[17,12,0,18,6,"INT"],[18,17,16,18,7,"COMBO"],[19,23,0,19,0,"MODEL"],[20,18,0,19,1,"CONDITIONING"],[21,13,0,19,2,"CONDITIONING"],[22,14,0,19,3,"LATENT"],[23,23,0,21,0,"MODEL"],[24,15,0,23,0,"MODEL"],[25,22,0,24,0,"NOISE"],[26,19,0,24,1,"GUIDER"],[27,20,0,24,2,"SAMPLER"],[28,21,0,24,3,"SIGMAS"],[29,14,0,24,4,"LATENT"],[30,29,0,25,0,"AUDIO"],[31,24,1,26,0,"LATENT"],[32,15,2,26,1,"VAE"],[33,26,0,27,0,"AUDIO"],[34,10,0,28,0,"AUDIO"],[35,16,0,29,0,"AUDIO"]],"groups":[{"id":1,"title":"Load Model","bounding":[453.34038296508766,43.329047424316286,448,182],"color":"#3f789e","font_size":24,"flags":{}},{"id":2,"title":"Duration","bounding":[453.34038296508766,243.3290474243163,450,170],"color":"#3f789e","font_size":24,"flags":{}},{"id":3,"title":"COVER","bounding":[933.3403829650877,43.329047424316286,640,820],"color":"#3f789e","font_size":24,"flags":{}},{"id":4,"title":"Guider","bounding":[1614.1331541109707,48.050058642859426,1329.466728210446,814.800117492674],"color":"#3f789e","font_size":24,"flags":{}},{"id":5,"title":"Group","bounding":[2980.685405293525,50.92808060521634,1011.9334564208966,839.0000839233378],"color":"#3f789e","font_size":24,"flags":{}}],"config":{},"extra":{"ds":{"scale":1.6105100000000008,"offset":[277.4288227725874,24.50885306740408]},"workflowRendererVersion":"LG"},"version":0.4} \ No newline at end of file +{ + "id": "5053cd4b-bb11-4361-b515-8844ef227a1c", + "revision": 0, + "last_node_id": 31, + "last_link_id": 47, + "nodes": [ + { + "id": 12, + "type": "PrimitiveNode", + "pos": [ + 551.3403829650877, + 319.3290474243163 + ], + "size": [ + 278, + 82 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "INT", + "type": "INT", + "widget": { + "name": "duration" + }, + "links": [ + 44 + ] + } + ], + "title": "Song Duration", + "properties": { + "Run widget replace on values": false + }, + "widgets_values": [ + 60, + "fixed" + ] + }, + { + "id": 15, + "type": "CheckpointLoaderSimple", + "pos": [ + 463.34038296508766, + 113.32904742431629 + ], + "size": [ + 428, + 98 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 24 + ] + }, + { + "name": "CLIP", + "type": "CLIP", + "links": [ + 42 + ] + }, + { + "name": "VAE", + "type": "VAE", + "links": [ + 13, + 32 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "CheckpointLoaderSimple" + }, + "widgets_values": [ + "ace_step_1.5_turbo_aio.safetensors" + ] + }, + { + "id": 17, + "type": "AudioInfo", + "pos": [ + 561.3403829650877, + 474.3290474243163 + ], + "size": [ + 270, + 378 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 14 + } + ], + "outputs": [ + { + "name": "total_frames", + "type": "INT", + "links": null + }, + { + "name": "frames_per_beat", + "type": "INT", + "links": null + }, + { + "name": "frames_per_bar", + "type": "INT", + "links": null + }, + { + "name": "frames_per_quarter", + "type": "INT", + "links": null + }, + { + "name": "frames_per_eighth", + "type": "INT", + "links": null + }, + { + "name": "audio_duration", + "type": "FLOAT", + "links": null + }, + { + "name": "beats_per_second", + "type": "FLOAT", + "links": null + }, + { + "name": "detected_bpm", + "type": "FLOAT", + "links": [] + }, + { + "name": "detected_bpm_rounded", + "type": "INT", + "links": [ + 43 + ] + }, + { + "name": "sample_rate", + "type": "INT", + "links": null + }, + { + "name": "num_channels", + "type": "INT", + "links": null + }, + { + "name": "num_samples", + "type": "INT", + "links": null + }, + { + "name": "max_amplitude", + "type": "FLOAT", + "links": null + }, + { + "name": "mean_amplitude", + "type": "FLOAT", + "links": null + }, + { + "name": "rms_amplitude", + "type": "FLOAT", + "links": null + }, + { + "name": "bit_depth", + "type": "STRING", + "links": null + }, + { + "name": "detected_key", + "type": "COMBO", + "links": [ + 45 + ] + } + ], + "properties": { + "cnr_id": "comfyui_ryanontheinside", + "ver": "418dd269462f0f08096ae5ab899f991500f3a44c", + "Node name for S&R": "AudioInfo" + }, + "widgets_values": [ + 30 + ] + }, + { + "id": 19, + "type": "ACEStep15NativeCoverGuider", + "pos": [ + 2120.660994667053, + 294.4027658107756 + ], + "size": [ + 359, + 146 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 19 + }, + { + "name": "positive", + "type": "CONDITIONING", + "link": 46 + }, + { + "name": "negative", + "type": "CONDITIONING", + "link": 21 + }, + { + "name": "source_latents", + "type": "LATENT", + "link": 22 + }, + { + "name": "semantic_hints", + "shape": 7, + "type": "SEMANTIC_HINTS", + "link": null + } + ], + "outputs": [ + { + "name": "GUIDER", + "type": "GUIDER", + "links": [ + 26 + ] + } + ], + "properties": { + "cnr_id": "comfyui_ryanontheinside", + "ver": "418dd269462f0f08096ae5ab899f991500f3a44c", + "Node name for S&R": "ACEStep15NativeCoverGuider" + }, + "widgets_values": [ + 1 + ] + }, + { + "id": 20, + "type": "KSamplerSelect", + "pos": [ + 2160.660994667053, + 494.4027658107756 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "SAMPLER", + "type": "SAMPLER", + "links": [ + 27 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "KSamplerSelect" + }, + "widgets_values": [ + "euler" + ] + }, + { + "id": 22, + "type": "RandomNoise", + "pos": [ + 2130.660994667053, + 144.40276581077512 + ], + "size": [ + 315, + 82 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "NOISE", + "type": "NOISE", + "links": [ + 25 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "RandomNoise" + }, + "widgets_values": [ + 990, + "fixed" + ] + }, + { + "id": 23, + "type": "ModelSamplingAuraFlow", + "pos": [ + 1693.1675673904415, + 282.3494657161712 + ], + "size": [ + 330, + 60 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 24 + } + ], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 19, + 23 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "ModelSamplingAuraFlow" + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 25, + "type": "PreviewAudio", + "pos": [ + 3569.0547222900386, + 756.6726754379266 + ], + "size": [ + 270, + 88 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 30 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "PreviewAudio" + }, + "widgets_values": [] + }, + { + "id": 26, + "type": "VAEDecodeAudio", + "pos": [ + 3032.9211315917964, + 396.2059891891478 + ], + "size": [ + 190, + 46 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "name": "samples", + "type": "LATENT", + "link": 31 + }, + { + "name": "vae", + "type": "VAE", + "link": 32 + } + ], + "outputs": [ + { + "name": "AUDIO", + "type": "AUDIO", + "links": [ + 10, + 33 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "VAEDecodeAudio" + }, + "widgets_values": [] + }, + { + "id": 29, + "type": "Reroute", + "pos": [ + 3238.9883465576168, + 754.4726250839233 + ], + "size": [ + 75, + 26 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "", + "type": "*", + "link": 35 + } + ], + "outputs": [ + { + "name": "", + "type": "AUDIO", + "links": [ + 30 + ] + } + ], + "properties": { + "showOutputText": false, + "horizontal": false + } + }, + { + "id": 11, + "type": "MarkdownNote", + "pos": [ + -6.659617034912344, + 73.32904742431629 + ], + "size": [ + 420, + 360 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "## ACE-Step 1.5 Cover Workflow\n\nAceStep1.5 Cover task\n\nGenerates new content across the entire duration while using the source audio structure as guidance.\n\n**Model:**\n- [ace_step_1.5_turbo_aio.safetensors](https://huggingface.co/Comfy-Org/ace_step_1.5_ComfyUI_files/resolve/main/checkpoints/ace_step_1.5_turbo_aio.safetensors)\n\n## [gimmi stars on github](https://github.com/ryanontheinside/ComfyUI_RyanOnTheInside)\n\n## [follow me on youtube](https://www.youtube.com/@ryanontheinside)" + ], + "color": "#222", + "bgcolor": "#000" + }, + { + "id": 14, + "type": "VAEEncodeAudio", + "pos": [ + 1302.340260894776, + 791.9956917114259 + ], + "size": [ + 210, + 46 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 12 + }, + { + "name": "vae", + "type": "VAE", + "link": 13 + } + ], + "outputs": [ + { + "name": "LATENT", + "type": "LATENT", + "links": [ + 22, + 29 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "VAEEncodeAudio" + }, + "widgets_values": [] + }, + { + "id": 13, + "type": "ConditioningZeroOut", + "pos": [ + 1312.8936002502437, + 714.6023047485352 + ], + "size": [ + 204.134765625, + 26 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "conditioning", + "type": "CONDITIONING", + "link": 47 + } + ], + "outputs": [ + { + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 21 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "ConditioningZeroOut" + }, + "widgets_values": [] + }, + { + "id": 24, + "type": "SamplerCustomAdvanced", + "pos": [ + 2643.7276572647106, + 475.6027696254728 + ], + "size": [ + 212.3638671875, + 106 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "noise", + "type": "NOISE", + "link": 25 + }, + { + "name": "guider", + "type": "GUIDER", + "link": 26 + }, + { + "name": "sampler", + "type": "SAMPLER", + "link": 27 + }, + { + "name": "sigmas", + "type": "SIGMAS", + "link": 28 + }, + { + "name": "latent_image", + "type": "LATENT", + "link": 29 + } + ], + "outputs": [ + { + "name": "output", + "type": "LATENT", + "links": [] + }, + { + "name": "denoised_output", + "type": "LATENT", + "links": [ + 31 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "SamplerCustomAdvanced" + }, + "widgets_values": [] + }, + { + "id": 21, + "type": "BasicScheduler", + "pos": [ + 2193.9943320693965, + 621.0694162014005 + ], + "size": [ + 270, + 106 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 23 + } + ], + "outputs": [ + { + "name": "SIGMAS", + "type": "SIGMAS", + "links": [ + 28 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "BasicScheduler" + }, + "widgets_values": [ + "simple", + 30, + 1 + ] + }, + { + "id": 16, + "type": "VHS_LoadAudioUpload", + "pos": [ + 259.34038296508766, + 484.3290474243163 + ], + "size": [ + 252.0078125, + 204 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "audio", + "type": "AUDIO", + "links": [ + 12, + 14, + 35 + ] + }, + { + "name": "duration", + "type": "FLOAT", + "links": null + } + ], + "properties": { + "cnr_id": "comfyui-videohelpersuite", + "ver": "1.7.7", + "Node name for S&R": "VHS_LoadAudioUpload" + }, + "widgets_values": { + "audio": "Vesuvius_v2_edit.wav", + "start_time": 0, + "duration": 60, + "audiopreview": { + "params": { + "filename": "Vesuvius_v2_edit.wav", + "type": "input", + "start_time": 0, + "duration": 60 + } + } + } + }, + { + "id": 31, + "type": "ACEStep15TaskTextEncode", + "pos": [ + 998.2009740447447, + 183.37259358107588 + ], + "size": [ + 400, + 454 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "CLIP", + "link": 42 + }, + { + "name": "bpm", + "shape": 7, + "type": "INT", + "widget": { + "name": "bpm" + }, + "link": 43 + }, + { + "name": "duration", + "shape": 7, + "type": "INT", + "widget": { + "name": "duration" + }, + "link": 44 + }, + { + "name": "keyscale", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "keyscale" + }, + "link": 45 + } + ], + "outputs": [ + { + "name": "conditioning", + "type": "CONDITIONING", + "links": [ + 46, + 47 + ] + } + ], + "properties": { + "cnr_id": "comfyui_ryanontheinside", + "ver": "6916a14dbfe0178b62b5c1a27d53df4abbe00e2c", + "Node name for S&R": "ACEStep15TaskTextEncode" + }, + "widgets_values": [ + "jazz piano cover with swing rhythm ", + "cover", + "", + "", + 120, + 60, + "C major", + "4", + "en", + 0, + "fixed", + 2, + 0.85, + 0.9, + 0 + ] + }, + { + "id": 27, + "type": "SaveAudioMP3", + "pos": [ + 3425.7892344217885, + 136.61124982383402 + ], + "size": [ + 424.16007385253897, + 147.58003692626949 + ], + "flags": {}, + "order": 18, + "mode": 4, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 33 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "SaveAudioMP3" + }, + "widgets_values": [ + "audio/ace_step_cover", + "V0" + ] + }, + { + "id": 10, + "type": "Knob", + "pos": [ + 3268.913320699689, + 437.21562922638856 + ], + "size": [ + 270, + 122 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 10 + } + ], + "outputs": [ + { + "name": "AUDIO", + "type": "AUDIO", + "links": [ + 34 + ] + } + ], + "properties": { + "cnr_id": "comfyui_ryanontheinside", + "ver": "951b1318f8958bfc441c0bcbbf2fc0695e1d9278", + "Node name for S&R": "Knob" + }, + "widgets_values": [ + 0.2, + 0.05 + ] + }, + { + "id": 28, + "type": "PreviewAudio", + "pos": [ + 3578.36207022555, + 448.2548972588441 + ], + "size": [ + 385.1337451171876, + 90.93334899902345 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 34 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "PreviewAudio" + }, + "widgets_values": [] + } + ], + "links": [ + [ + 10, + 26, + 0, + 10, + 0, + "AUDIO" + ], + [ + 12, + 16, + 0, + 14, + 0, + "AUDIO" + ], + [ + 13, + 15, + 2, + 14, + 1, + "VAE" + ], + [ + 14, + 16, + 0, + 17, + 0, + "AUDIO" + ], + [ + 19, + 23, + 0, + 19, + 0, + "MODEL" + ], + [ + 21, + 13, + 0, + 19, + 2, + "CONDITIONING" + ], + [ + 22, + 14, + 0, + 19, + 3, + "LATENT" + ], + [ + 23, + 23, + 0, + 21, + 0, + "MODEL" + ], + [ + 24, + 15, + 0, + 23, + 0, + "MODEL" + ], + [ + 25, + 22, + 0, + 24, + 0, + "NOISE" + ], + [ + 26, + 19, + 0, + 24, + 1, + "GUIDER" + ], + [ + 27, + 20, + 0, + 24, + 2, + "SAMPLER" + ], + [ + 28, + 21, + 0, + 24, + 3, + "SIGMAS" + ], + [ + 29, + 14, + 0, + 24, + 4, + "LATENT" + ], + [ + 30, + 29, + 0, + 25, + 0, + "AUDIO" + ], + [ + 31, + 24, + 1, + 26, + 0, + "LATENT" + ], + [ + 32, + 15, + 2, + 26, + 1, + "VAE" + ], + [ + 33, + 26, + 0, + 27, + 0, + "AUDIO" + ], + [ + 34, + 10, + 0, + 28, + 0, + "AUDIO" + ], + [ + 35, + 16, + 0, + 29, + 0, + "AUDIO" + ], + [ + 42, + 15, + 1, + 31, + 0, + "CLIP" + ], + [ + 43, + 17, + 8, + 31, + 1, + "INT" + ], + [ + 44, + 12, + 0, + 31, + 2, + "INT" + ], + [ + 45, + 17, + 16, + 31, + 3, + "COMBO" + ], + [ + 46, + 31, + 0, + 19, + 1, + "CONDITIONING" + ], + [ + 47, + 31, + 0, + 13, + 0, + "CONDITIONING" + ] + ], + "groups": [ + { + "id": 1, + "title": "Load Model", + "bounding": [ + 453.34038296508766, + 43.329047424316286, + 448, + 182 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 2, + "title": "Duration", + "bounding": [ + 453.34038296508766, + 243.3290474243163, + 450, + 170 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 3, + "title": "COVER", + "bounding": [ + 933.3403829650877, + 43.329047424316286, + 640, + 820 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 4, + "title": "Guider", + "bounding": [ + 1614.1331541109707, + 48.050058642859426, + 1329.466728210446, + 814.800117492674 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + }, + { + "id": 5, + "title": "Group", + "bounding": [ + 2980.685405293525, + 50.92808060521634, + 1011.9334564208966, + 839.0000839233378 + ], + "color": "#3f789e", + "font_size": 24, + "flags": {} + } + ], + "config": {}, + "extra": { + "ds": { + "scale": 0.751314800901578, + "offset": [ + -123.93750962616554, + 415.956160509102 + ] + }, + "workflowRendererVersion": "LG", + "frontendVersion": "1.37.11", + "VHS_latentpreview": false, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true + }, + "version": 0.4 +} \ No newline at end of file diff --git a/examples/ace1.5/audio_ace_step_1_5_edit.json b/examples/ace1.5/audio_ace_step_1_5_edit.json index 96ae9c7..106e53b 100644 --- a/examples/ace1.5/audio_ace_step_1_5_edit.json +++ b/examples/ace1.5/audio_ace_step_1_5_edit.json @@ -1,8 +1,8 @@ { "id": "1321ed79-5bbf-44b4-a7f2-cc6914f8ed3c", "revision": 0, - "last_node_id": 18, - "last_link_id": 24, + "last_node_id": 21, + "last_link_id": 37, "nodes": [ { "id": 1, @@ -31,7 +31,7 @@ "name": "CLIP", "type": "CLIP", "links": [ - 2 + 32 ] }, { @@ -75,7 +75,7 @@ "name": "duration" }, "links": [ - 4 + 34 ] } ], @@ -204,157 +204,6 @@ "euler" ] }, - { - "id": 12, - "type": "RandomNoise", - "pos": [ - 1881.1492814143214, - 84.68943578981373 - ], - "size": [ - 315, - 82 - ], - "flags": {}, - "order": 3, - "mode": 0, - "inputs": [], - "outputs": [ - { - "name": "NOISE", - "type": "NOISE", - "links": [ - 14 - ] - } - ], - "properties": { - "cnr_id": "comfy-core", - "ver": "0.12.2", - "Node name for S&R": "RandomNoise" - }, - "widgets_values": [ - 990, - "fixed" - ] - }, - { - "id": 13, - "type": "ModelSamplingAuraFlow", - "pos": [ - 1491.5184221515126, - 124.43989184642457 - ], - "size": [ - 330, - 60 - ], - "flags": {}, - "order": 6, - "mode": 0, - "inputs": [ - { - "name": "model", - "type": "MODEL", - "link": 19 - } - ], - "outputs": [ - { - "name": "MODEL", - "type": "MODEL", - "links": [ - 9, - 10 - ] - } - ], - "properties": { - "cnr_id": "comfy-core", - "ver": "0.12.2", - "Node name for S&R": "ModelSamplingAuraFlow" - }, - "widgets_values": [ - 3 - ] - }, - { - "id": 5, - "type": "ConditioningZeroOut", - "pos": [ - 1546.6533669910605, - 572.241559278368 - ], - "size": [ - 204.134765625, - 26 - ], - "flags": {}, - "order": 12, - "mode": 0, - "inputs": [ - { - "name": "conditioning", - "type": "CONDITIONING", - "link": 6 - } - ], - "outputs": [ - { - "name": "CONDITIONING", - "type": "CONDITIONING", - "links": [ - 12 - ] - } - ], - "properties": { - "cnr_id": "comfy-core", - "ver": "0.12.2", - "Node name for S&R": "ConditioningZeroOut" - }, - "widgets_values": [] - }, - { - "id": 15, - "type": "Knob", - "pos": [ - 2774.678850395049, - 285.9556615665655 - ], - "size": [ - 270, - 122 - ], - "flags": {}, - "order": 16, - "mode": 0, - "inputs": [ - { - "name": "audio", - "type": "AUDIO", - "link": 22 - } - ], - "outputs": [ - { - "name": "AUDIO", - "type": "AUDIO", - "links": [ - 24 - ] - } - ], - "properties": { - "cnr_id": "comfyui_ryanontheinside", - "ver": "951b1318f8958bfc441c0bcbbf2fc0695e1d9278", - "Node name for S&R": "Knob" - }, - "widgets_values": [ - 0.2, - 0.05 - ] - }, { "id": 11, "type": "MarkdownNote", @@ -367,7 +216,7 @@ 400 ], "flags": {}, - "order": 4, + "order": 3, "mode": 0, "inputs": [], "outputs": [], @@ -444,7 +293,7 @@ "name": "detected_bpm_rounded", "type": "INT", "links": [ - 3 + 33 ] }, { @@ -486,7 +335,7 @@ "name": "detected_key", "type": "COMBO", "links": [ - 5 + 35 ] } ], @@ -499,112 +348,6 @@ 30 ] }, - { - "id": 17, - "type": "PreviewAudio", - "pos": [ - 3124.678850395049, - 485.9556615665655 - ], - "size": [ - 270, - 88 - ], - "flags": {}, - "order": 9, - "mode": 0, - "inputs": [ - { - "name": "audio", - "type": "AUDIO", - "link": 23 - } - ], - "outputs": [], - "properties": { - "cnr_id": "comfy-core", - "ver": "0.12.2", - "Node name for S&R": "PreviewAudio" - }, - "widgets_values": [] - }, - { - "id": 4, - "type": "ACEStep15TaskTextEncode", - "pos": [ - 830, - 200 - ], - "size": [ - 400, - 358 - ], - "flags": {}, - "order": 11, - "mode": 0, - "inputs": [ - { - "name": "clip", - "type": "CLIP", - "link": 2 - }, - { - "name": "bpm", - "shape": 7, - "type": "INT", - "widget": { - "name": "bpm" - }, - "link": 3 - }, - { - "name": "duration", - "shape": 7, - "type": "INT", - "widget": { - "name": "duration" - }, - "link": 4 - }, - { - "name": "keyscale", - "shape": 7, - "type": "COMBO", - "widget": { - "name": "keyscale" - }, - "link": 5 - } - ], - "outputs": [ - { - "name": "conditioning", - "type": "CONDITIONING", - "links": [ - 6, - 11 - ] - } - ], - "properties": { - "cnr_id": "comfyui_ryanontheinside", - "ver": "418dd269462f0f08096ae5ab899f991500f3a44c", - "Node name for S&R": "ACEStep15TaskTextEncode" - }, - "widgets_values": [ - "continue the melodic electronic track with soft synths", - "repaint", - "", - "", - 120, - 60, - "C major", - "4", - "en", - 0, - "fixed" - ] - }, { "id": 16, "type": "VHS_LoadAudioUpload", @@ -617,7 +360,7 @@ 204 ], "flags": {}, - "order": 5, + "order": 4, "mode": 0, "inputs": [], "outputs": [ @@ -655,103 +398,6 @@ } } }, - { - "id": 8, - "type": "ACEStep15NativeEditGuider", - "pos": [ - 1841.1492814143214, - 504.68943578981373 - ], - "size": [ - 449.1958984375, - 214 - ], - "flags": {}, - "order": 13, - "mode": 0, - "inputs": [ - { - "name": "model", - "type": "MODEL", - "link": 10 - }, - { - "name": "positive", - "type": "CONDITIONING", - "link": 11 - }, - { - "name": "negative", - "type": "CONDITIONING", - "link": 12 - }, - { - "name": "source_latents", - "type": "LATENT", - "link": 13 - } - ], - "outputs": [ - { - "name": "guider", - "type": "GUIDER", - "links": [ - 15 - ] - }, - { - "name": "output_latent", - "type": "LATENT", - "links": [ - 18 - ] - } - ], - "properties": { - "cnr_id": "comfyui_ryanontheinside", - "ver": "98474ec06548c527400ca866ca65f2b4c477712b", - "Node name for S&R": "ACEStep15NativeEditGuider" - }, - "widgets_values": [ - 1, - 10, - 20, - -1, - -1 - ] - }, - { - "id": 18, - "type": "SaveAudioMP3", - "pos": [ - 3104.678850395049, - 225.9556615665654 - ], - "size": [ - 550, - 150 - ], - "flags": {}, - "order": 17, - "mode": 0, - "inputs": [ - { - "name": "audio", - "type": "AUDIO", - "link": 24 - } - ], - "outputs": [], - "properties": { - "cnr_id": "comfy-core", - "ver": "0.12.2", - "Node name for S&R": "SaveAudioMP3" - }, - "widgets_values": [ - "audio/ace_step_edit", - "V0" - ] - }, { "id": 10, "type": "SamplerCustomAdvanced", @@ -855,6 +501,394 @@ "Node name for S&R": "VAEDecodeAudio" }, "widgets_values": [] + }, + { + "id": 12, + "type": "RandomNoise", + "pos": [ + 1881.1492814143214, + 84.68943578981373 + ], + "size": [ + 315, + 82 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "NOISE", + "type": "NOISE", + "links": [ + 14 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "RandomNoise" + }, + "widgets_values": [ + 990, + "fixed" + ] + }, + { + "id": 13, + "type": "ModelSamplingAuraFlow", + "pos": [ + 1483.3770112170293, + 213.99568542833242 + ], + "size": [ + 330, + 60 + ], + "flags": {}, + "order": 6, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 19 + } + ], + "outputs": [ + { + "name": "MODEL", + "type": "MODEL", + "links": [ + 9, + 10 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "ModelSamplingAuraFlow" + }, + "widgets_values": [ + 3 + ] + }, + { + "id": 5, + "type": "ConditioningZeroOut", + "pos": [ + 1549.6438846171673, + 522.8995242470139 + ], + "size": [ + 204.134765625, + 26 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "conditioning", + "type": "CONDITIONING", + "link": 37 + } + ], + "outputs": [ + { + "name": "CONDITIONING", + "type": "CONDITIONING", + "links": [ + 12 + ] + } + ], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "ConditioningZeroOut" + }, + "widgets_values": [] + }, + { + "id": 8, + "type": "ACEStep15NativeEditGuider", + "pos": [ + 1841.1492814143214, + 504.68943578981373 + ], + "size": [ + 449.1958984375, + 214 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "MODEL", + "link": 10 + }, + { + "name": "positive", + "type": "CONDITIONING", + "link": 36 + }, + { + "name": "negative", + "type": "CONDITIONING", + "link": 12 + }, + { + "name": "source_latents", + "type": "LATENT", + "link": 13 + } + ], + "outputs": [ + { + "name": "guider", + "type": "GUIDER", + "links": [ + 15 + ] + }, + { + "name": "output_latent", + "type": "LATENT", + "links": [ + 18 + ] + } + ], + "properties": { + "cnr_id": "comfyui_ryanontheinside", + "ver": "98474ec06548c527400ca866ca65f2b4c477712b", + "Node name for S&R": "ACEStep15NativeEditGuider" + }, + "widgets_values": [ + 1, + 50, + 0, + -1, + -1 + ] + }, + { + "id": 17, + "type": "PreviewAudio", + "pos": [ + 3095.4712065784292, + 649.9685267381775 + ], + "size": [ + 270, + 88 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 23 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "PreviewAudio" + }, + "widgets_values": [] + }, + { + "id": 18, + "type": "SaveAudioMP3", + "pos": [ + 3104.678850395049, + 225.9556615665654 + ], + "size": [ + 550, + 150 + ], + "flags": {}, + "order": 17, + "mode": 4, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 24 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "SaveAudioMP3" + }, + "widgets_values": [ + "audio/ace_step_edit", + "V0" + ] + }, + { + "id": 15, + "type": "Knob", + "pos": [ + 2774.678850395049, + 285.9556615665655 + ], + "size": [ + 270, + 122 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 22 + } + ], + "outputs": [ + { + "name": "AUDIO", + "type": "AUDIO", + "links": [ + 24, + 31 + ] + } + ], + "properties": { + "cnr_id": "comfyui_ryanontheinside", + "ver": "951b1318f8958bfc441c0bcbbf2fc0695e1d9278", + "Node name for S&R": "Knob" + }, + "widgets_values": [ + 0.2, + 0.05 + ] + }, + { + "id": 20, + "type": "PreviewAudio", + "pos": [ + 3135.2957876492387, + 456.13105221252147 + ], + "size": [ + 512.6491099499931, + 95.86364427610226 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "name": "audio", + "type": "AUDIO", + "link": 31 + } + ], + "outputs": [], + "properties": { + "cnr_id": "comfy-core", + "ver": "0.12.2", + "Node name for S&R": "PreviewAudio" + }, + "widgets_values": [] + }, + { + "id": 21, + "type": "ACEStep15TaskTextEncode", + "pos": [ + 803.9301858347135, + 103.54510660775249 + ], + "size": [ + 400, + 454 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [ + { + "name": "clip", + "type": "CLIP", + "link": 32 + }, + { + "name": "bpm", + "shape": 7, + "type": "INT", + "widget": { + "name": "bpm" + }, + "link": 33 + }, + { + "name": "duration", + "shape": 7, + "type": "INT", + "widget": { + "name": "duration" + }, + "link": 34 + }, + { + "name": "keyscale", + "shape": 7, + "type": "COMBO", + "widget": { + "name": "keyscale" + }, + "link": 35 + } + ], + "outputs": [ + { + "name": "conditioning", + "type": "CONDITIONING", + "links": [ + 36, + 37 + ] + } + ], + "properties": { + "cnr_id": "comfyui_ryanontheinside", + "ver": "dfb20755f852feb95d88bc39f9c00a6dc1a96d9d", + "Node name for S&R": "ACEStep15TaskTextEncode" + }, + "widgets_values": [ + "continue the melodic electronic track with soft synths", + "repaint", + "", + "", + 120, + 60, + "C major", + "4", + "en", + 0, + "fixed", + 2, + 0.85, + 0.9, + 0 + ] } ], "links": [ @@ -866,46 +900,6 @@ 0, "AUDIO" ], - [ - 2, - 1, - 1, - 4, - 0, - "CLIP" - ], - [ - 3, - 3, - 8, - 4, - 1, - "INT" - ], - [ - 4, - 2, - 0, - 4, - 2, - "INT" - ], - [ - 5, - 3, - 16, - 4, - 3, - "COMBO" - ], - [ - 6, - 4, - 0, - 5, - 0, - "CONDITIONING" - ], [ 7, 16, @@ -938,14 +932,6 @@ 0, "MODEL" ], - [ - 11, - 4, - 0, - 8, - 1, - "CONDITIONING" - ], [ 12, 5, @@ -1049,6 +1035,62 @@ 18, 0, "AUDIO" + ], + [ + 31, + 15, + 0, + 20, + 0, + "AUDIO" + ], + [ + 32, + 1, + 1, + 21, + 0, + "CLIP" + ], + [ + 33, + 3, + 8, + 21, + 1, + "INT" + ], + [ + 34, + 2, + 0, + 21, + 2, + "INT" + ], + [ + 35, + 3, + 16, + 21, + 3, + "COMBO" + ], + [ + 36, + 21, + 0, + 8, + 1, + "CONDITIONING" + ], + [ + 37, + 21, + 0, + 5, + 0, + "CONDITIONING" ] ], "groups": [ @@ -1121,10 +1163,10 @@ "config": {}, "extra": { "ds": { - "scale": 0.4177248169415674, + "scale": 0.6699734054070322, "offset": [ - 605.3831100907462, - 1103.4212377905055 + 367.6347128636378, + 406.24180511074536 ] }, "workflowRendererVersion": "LG", diff --git a/nodes/acestep/nodes.py b/nodes/acestep/nodes.py index fc2c842..3d907d5 100644 --- a/nodes/acestep/nodes.py +++ b/nodes/acestep/nodes.py @@ -975,7 +975,8 @@ class ACEStep15TaskTextEncodeNode: "required": { "clip": ("CLIP",), "text": ("STRING", {"multiline": True, "dynamicPrompts": True, "default": "A melodic electronic track with soft synths"}), - "task_type": (["text2music", "repaint", "cover"],), # TODO: Re-enable "extract", "lego" when ready + "task_type": (["text2music", "repaint", "cover"], + {"tooltip": "text2music/repaint use LM audio code generation (cfg_scale, temperature, top_p, top_k apply). cover uses precomputed semantic hints from source audio instead."}), # TODO: Re-enable "extract", "lego" when ready }, "optional": { "track_name": (["", "vocals", "drums", "bass", "guitar", "keyboard", "strings", @@ -989,6 +990,14 @@ class ACEStep15TaskTextEncodeNode: "timesignature": ("COMBO", {"default": "4", "options": s.VALID_TIME_SIGNATURES}), "language": ("COMBO", {"default": "en", "options": s.VALID_LANGUAGES}), "seed": ("INT", {"default": 0, "min": 0, "max": 0xffffffff}), + "cfg_scale": ("FLOAT", {"default": 2.0, "min": 0.0, "max": 100.0, "step": 0.1, + "tooltip": "Controls how closely the generated audio follows your text prompt. Higher values produce output that matches your description more literally, lower values allow more freedom. No effect on cover/extract/lego tasks, which use semantic hints from source audio instead of generating new audio codes."}), + "temperature": ("FLOAT", {"default": 0.85, "min": 0.0, "max": 2.0, "step": 0.01, + "tooltip": "Controls randomness and creativity in the generated audio. Lower values (0.7-0.85) produce more consistent, predictable results. Higher values (0.9-1.1) produce more varied, surprising output. No effect on cover/extract/lego tasks, which use semantic hints from source audio instead of generating new audio codes."}), + "top_p": ("FLOAT", {"default": 0.9, "min": 0.0, "max": 1.0, "step": 0.01, + "tooltip": "Limits how many possible audio choices are considered at each step. Lower values (e.g. 0.8) produce safer, more predictable output. Higher values allow more diversity. 1.0 disables this filter. No effect on cover/extract/lego tasks, which use semantic hints from source audio instead of generating new audio codes."}), + "top_k": ("INT", {"default": 0, "min": 0, "max": 100, + "tooltip": "Restricts each generation step to only the top K most likely choices. 0 disables this filter. Lower values (e.g. 40) reduce unlikely outputs while keeping variety. No effect on cover/extract/lego tasks, which use semantic hints from source audio instead of generating new audio codes."}), } } @@ -998,7 +1007,8 @@ class ACEStep15TaskTextEncodeNode: CATEGORY = "conditioning" def encode(self, clip, text, task_type, track_name="", lyrics="", bpm=120, - duration=60, keyscale="C major", timesignature="4", language="en", seed=0): + duration=60, keyscale="C major", timesignature="4", language="en", seed=0, + cfg_scale=2.0, temperature=0.85, top_p=0.9, top_k=0): # Validate track_name for extract/lego tasks if task_type in ["extract", "lego"] and not track_name: logger.debug(f"[ACE15_TEXT_ENCODE] Warning: track_name not specified for {task_type} task, using default instruction") @@ -1017,9 +1027,14 @@ class ACEStep15TaskTextEncodeNode: "seed": seed, "task_type": task_type, "track_name": track_name if track_name else None, + "cfg_scale": cfg_scale, + "temperature": temperature, + "top_p": top_p, + "top_k": top_k, } logger.debug(f"[ACE15_TEXT_ENCODE] Encoding with task_type={task_type}, track_name={track_name or 'N/A'}") + print(f"[ACE15_TEXT_ENCODE] LM params: cfg_scale={cfg_scale}, temperature={temperature}, top_p={top_p}, top_k={top_k}") # Import to get task instruction for verification from .patches import get_task_instruction, is_patched diff --git a/nodes/acestep/patches.py b/nodes/acestep/patches.py index 9875e78..ffb9714 100644 --- a/nodes/acestep/patches.py +++ b/nodes/acestep/patches.py @@ -214,9 +214,11 @@ def _create_patched_tokenizer(original_tokenize_with_weights): # Strip our custom kwargs before forwarding to the stock tokenizer stock_kwargs = {k: v for k, v in kwargs.items() if k not in ("task_type", "track_name")} + print(f"[ACE15_PATCHED_TOKENIZER] stock_kwargs LM params: cfg_scale={stock_kwargs.get('cfg_scale', 'MISSING')}, temperature={stock_kwargs.get('temperature', 'MISSING')}, top_p={stock_kwargs.get('top_p', 'MISSING')}, top_k={stock_kwargs.get('top_k', 'MISSING')}") # Call the original tokenizer to get baseline output with all expected keys out = original_tokenize_with_weights(self, text, return_word_ids, **stock_kwargs) + print(f"[ACE15_PATCHED_TOKENIZER] lm_metadata after stock tokenizer: {out.get('lm_metadata', 'MISSING')}") # Get appropriate instruction for task type instruction = get_task_instruction(task_type, track_name) @@ -247,6 +249,7 @@ def _create_patched_tokenizer(original_tokenize_with_weights): out["task_type"] = task_type out["track_name"] = track_name + print(f"[ACE15_PATCHED_TOKENIZER] FINAL lm_metadata: {out.get('lm_metadata', 'MISSING')}") return out return patched_tokenize_with_weights