diff --git a/comfyui/workflows/text-to-music/diffrhythm-full-length-t2m-v1.json b/comfyui/workflows/text-to-music/diffrhythm-full-length-t2m-v1.json index 59e57c7..514c5fc 100644 --- a/comfyui/workflows/text-to-music/diffrhythm-full-length-t2m-v1.json +++ b/comfyui/workflows/text-to-music/diffrhythm-full-length-t2m-v1.json @@ -4,9 +4,9 @@ "nodes": [ { "id": 1, - "type": "DiffRhythmTextToMusic", + "type": "DiffRhythmRun", "pos": [100, 100], - "size": [400, 300], + "size": [400, 400], "flags": {}, "order": 0, "mode": 0, @@ -14,17 +14,23 @@ { "name": "AUDIO", "type": "AUDIO", - "links": [1] + "links": [1, 2] } ], - "properties": {}, + "properties": { + "Node name for S&R": "DiffRhythmRun" + }, "widgets_values": [ + "cfm_full_model.pt", "Cinematic orchestral piece with soaring strings, powerful brass, and emotional piano melodies building to an epic crescendo", - 285.0, - 3.5, + true, + "euler", + 30, + 4, + "quality", 123, - "cfm_full_model", - "auto" + false, + "[-1, 20], [60, -1]" ], "title": "DiffRhythm Full-Length Text-to-Music (4m45s)" }, @@ -43,7 +49,9 @@ "link": 1 } ], - "properties": {}, + "properties": { + "Node name for S&R": "PreviewAudio" + }, "title": "Preview Audio" }, { @@ -61,7 +69,9 @@ "link": 2 } ], - "properties": {}, + "properties": { + "Node name for S&R": "SaveAudio" + }, "widgets_values": [ "diffrhythm_full_output" ], @@ -90,12 +100,16 @@ "system_deps": ["espeak-ng"] }, "usage": { - "prompt": "Detailed text description of the desired full-length music composition", - "duration": "Fixed at 285 seconds (4m45s) for DiffRhythm Full model", - "guidance_scale": "Controls how closely the output follows the prompt (1.0-10.0, default: 3.5)", + "model": "cfm_full_model.pt (DiffRhythm Full - 4m45s/285s generation)", + "style_prompt": "Detailed text description of the desired full-length music composition", + "unload_model": "Boolean to unload model after generation (default: true)", + "odeint_method": "ODE solver: euler, midpoint, rk4, implicit_adams (default: euler)", + "steps": "Number of diffusion steps: 1-100 (default: 30)", + "cfg": "Classifier-free guidance scale: 1-10 (default: 4)", + "quality_or_speed": "Generation mode: quality or speed (default: quality for full-length)", "seed": "Random seed for reproducibility (default: 123)", - "model": "cfm_full_model (DiffRhythm Full - 4m45s generation)", - "device": "auto (automatic GPU selection)" + "edit": "Enable segment editing mode (default: false)", + "edit_segments": "Segments to edit when edit=true" }, "performance": { "generation_time": "~60-90 seconds on RTX 4090", @@ -105,9 +119,9 @@ "notes": [ "This workflow uses DiffRhythm Full for 4 minute 45 second music generation", "Best for complete song compositions with intro, development, and outro", - "All parameters are optional - can generate music randomly", + "All parameters except model and style_prompt are optional", "Supports complex, multi-part compositions", - "PLACEHOLDER: Actual node names and parameters need to be updated after ComfyUI_DiffRhythm installation" + "Can optionally connect MultiLineLyricsDR node for lyrics input" ] } }, diff --git a/comfyui/workflows/text-to-music/diffrhythm-random-generation-v1.json b/comfyui/workflows/text-to-music/diffrhythm-random-generation-v1.json index a6924b9..d0255e2 100644 --- a/comfyui/workflows/text-to-music/diffrhythm-random-generation-v1.json +++ b/comfyui/workflows/text-to-music/diffrhythm-random-generation-v1.json @@ -4,9 +4,9 @@ "nodes": [ { "id": 1, - "type": "DiffRhythmRandomGeneration", + "type": "DiffRhythmRun", "pos": [100, 100], - "size": [400, 250], + "size": [400, 400], "flags": {}, "order": 0, "mode": 0, @@ -14,15 +14,23 @@ { "name": "AUDIO", "type": "AUDIO", - "links": [1] + "links": [1, 2] } ], - "properties": {}, + "properties": { + "Node name for S&R": "DiffRhythmRun" + }, "widgets_values": [ - 95.0, + "cfm_model_v1_2.pt", + "", + true, + "euler", + 30, + 1, + "speed", -1, - "cfm_model_v1_2", - "auto" + false, + "[-1, 20], [60, -1]" ], "title": "DiffRhythm Random Generation (No Prompt)" }, @@ -41,7 +49,9 @@ "link": 1 } ], - "properties": {}, + "properties": { + "Node name for S&R": "PreviewAudio" + }, "title": "Preview Audio" }, { @@ -59,7 +69,9 @@ "link": 2 } ], - "properties": {}, + "properties": { + "Node name for S&R": "SaveAudio" + }, "widgets_values": [ "diffrhythm_random_output" ], @@ -88,10 +100,15 @@ "system_deps": ["espeak-ng"] }, "usage": { - "duration": "Fixed at 95 seconds for DiffRhythm 1.2 model", - "seed": "-1 (random seed each generation) or specific number for reproducibility", - "model": "cfm_model_v1_2 (DiffRhythm 1.2)", - "device": "auto (automatic GPU selection)", + "model": "cfm_model_v1_2.pt (DiffRhythm 1.2 - 95s generation)", + "style_prompt": "Empty string for random generation (no guidance)", + "unload_model": "Boolean to unload model after generation (default: true)", + "odeint_method": "ODE solver: euler (default)", + "steps": "Number of diffusion steps: 30 (default)", + "cfg": "Classifier-free guidance: 1 (minimal guidance for random output)", + "quality_or_speed": "Generation mode: speed (default)", + "seed": "-1 for random seed each generation, or specific number for reproducibility", + "edit": "false (no editing)", "note": "NO prompt, NO guidance, NO reference audio - pure random generation" }, "use_cases": [ @@ -106,16 +123,18 @@ "Use seed=-1 for completely random output each time", "Use fixed seed to reproduce interesting random results", "Batch process: Run 10-20 times to find interesting compositions", - "Save any interesting results with their seed numbers" + "Save any interesting results with their seed numbers", + "Empty style_prompt with cfg=1 produces truly random output" ], "notes": [ "This workflow demonstrates DiffRhythm's ability to generate music without any input", - "All DiffRhythm parameters are optional - this is the ultimate proof", + "All DiffRhythm parameters except model are at their most permissive settings", + "Empty string for style_prompt means no guidance from text", + "cfg=1 provides minimal guidance, maximizing randomness", "Results can range from ambient to energetic, classical to electronic", "Each generation is unique (with seed=-1)", "Generation time: ~30-60 seconds on RTX 4090", - "Perfect for discovering unexpected musical combinations", - "PLACEHOLDER: Actual node names and parameters need to be updated after ComfyUI_DiffRhythm installation" + "Perfect for discovering unexpected musical combinations" ] } }, diff --git a/comfyui/workflows/text-to-music/diffrhythm-reference-based-v1.json b/comfyui/workflows/text-to-music/diffrhythm-reference-based-v1.json index f3b97fb..5594c62 100644 --- a/comfyui/workflows/text-to-music/diffrhythm-reference-based-v1.json +++ b/comfyui/workflows/text-to-music/diffrhythm-reference-based-v1.json @@ -17,7 +17,9 @@ "links": [1] } ], - "properties": {}, + "properties": { + "Node name for S&R": "LoadAudio" + }, "widgets_values": [ "reference_audio.wav" ], @@ -25,15 +27,15 @@ }, { "id": 2, - "type": "DiffRhythmReferenceBasedGeneration", + "type": "DiffRhythmRun", "pos": [500, 100], - "size": [400, 350], + "size": [400, 450], "flags": {}, "order": 1, "mode": 0, "inputs": [ { - "name": "reference_audio", + "name": "style_audio_or_edit_song", "type": "AUDIO", "link": 1 } @@ -42,18 +44,23 @@ { "name": "AUDIO", "type": "AUDIO", - "links": [2] + "links": [2, 3] } ], - "properties": {}, + "properties": { + "Node name for S&R": "DiffRhythmRun" + }, "widgets_values": [ + "cfm_model_v1_2.pt", "Energetic rock music with driving guitar riffs and powerful drums", - 95.0, - 5.0, - 0.7, + true, + "euler", + 30, + 5, + "speed", 456, - "cfm_model_v1_2", - "auto" + false, + "[-1, 20], [60, -1]" ], "title": "DiffRhythm Reference-Based Generation" }, @@ -72,7 +79,9 @@ "link": 2 } ], - "properties": {}, + "properties": { + "Node name for S&R": "PreviewAudio" + }, "title": "Preview Generated Audio" }, { @@ -90,7 +99,9 @@ "link": 3 } ], - "properties": {}, + "properties": { + "Node name for S&R": "SaveAudio" + }, "widgets_values": [ "diffrhythm_reference_output" ], @@ -121,13 +132,16 @@ }, "usage": { "reference_audio": "Path to reference audio file (WAV, MP3, or other supported formats)", - "prompt": "Text description guiding the style and characteristics of generated music", - "duration": "Fixed at 95 seconds for DiffRhythm 1.2 model", - "guidance_scale": "Controls how closely output follows the prompt (1.0-10.0, default: 5.0)", - "reference_strength": "How much to follow the reference audio (0.0-1.0, default: 0.7)", + "model": "cfm_model_v1_2.pt (DiffRhythm 1.2)", + "style_prompt": "Text description guiding the style and characteristics of generated music", + "unload_model": "Boolean to unload model after generation (default: true)", + "odeint_method": "ODE solver: euler, midpoint, rk4, implicit_adams (default: euler)", + "steps": "Number of diffusion steps: 1-100 (default: 30)", + "cfg": "Classifier-free guidance scale: 1-10 (default: 5 for reference-based)", + "quality_or_speed": "Generation mode: quality or speed (default: speed)", "seed": "Random seed for reproducibility (default: 456)", - "model": "cfm_model_v1_2 (DiffRhythm 1.2)", - "device": "auto (automatic GPU selection)" + "edit": "Enable segment editing mode (default: false)", + "edit_segments": "Segments to edit when edit=true" }, "use_cases": [ "Style transfer: Apply the style of reference music to new prompt", @@ -137,11 +151,11 @@ ], "notes": [ "This workflow combines reference audio with text prompt guidance", - "Higher reference_strength (0.8-1.0) = closer to reference audio", - "Lower reference_strength (0.3-0.5) = more creative interpretation", - "Reference audio should ideally be similar duration to target (95s)", - "Can use any format supported by ComfyUI's audio loader", - "PLACEHOLDER: Actual node names and parameters need to be updated after ComfyUI_DiffRhythm installation" + "The reference audio is connected to the style_audio_or_edit_song input", + "Higher cfg values (7-10) = closer adherence to both prompt and reference", + "Lower cfg values (2-4) = more creative interpretation", + "Reference audio should ideally be similar duration to target (95s for cfm_model_v1_2.pt)", + "Can use any format supported by ComfyUI's LoadAudio node" ] } }, diff --git a/comfyui/workflows/text-to-music/diffrhythm-simple-t2m-v1.json b/comfyui/workflows/text-to-music/diffrhythm-simple-t2m-v1.json index 3e68775..f25f1bb 100644 --- a/comfyui/workflows/text-to-music/diffrhythm-simple-t2m-v1.json +++ b/comfyui/workflows/text-to-music/diffrhythm-simple-t2m-v1.json @@ -4,9 +4,9 @@ "nodes": [ { "id": 1, - "type": "DiffRhythmTextToMusic", + "type": "DiffRhythmRun", "pos": [100, 100], - "size": [400, 300], + "size": [400, 400], "flags": {}, "order": 0, "mode": 0, @@ -14,17 +14,23 @@ { "name": "AUDIO", "type": "AUDIO", - "links": [1] + "links": [1, 2] } ], - "properties": {}, + "properties": { + "Node name for S&R": "DiffRhythmRun" + }, "widgets_values": [ + "cfm_model_v1_2.pt", "Upbeat electronic dance music with energetic beats and synthesizer melodies", - 95.0, - 4.0, + true, + "euler", + 30, + 4, + "speed", 42, - "cfm_model_v1_2", - "auto" + false, + "[-1, 20], [60, -1]" ], "title": "DiffRhythm Text-to-Music (95s)" }, @@ -43,7 +49,9 @@ "link": 1 } ], - "properties": {}, + "properties": { + "Node name for S&R": "PreviewAudio" + }, "title": "Preview Audio" }, { @@ -61,7 +69,9 @@ "link": 2 } ], - "properties": {}, + "properties": { + "Node name for S&R": "SaveAudio" + }, "widgets_values": [ "diffrhythm_output" ], @@ -90,19 +100,23 @@ "system_deps": ["espeak-ng"] }, "usage": { - "prompt": "Text description of the desired music style, mood, and instruments", - "duration": "Fixed at 95 seconds for DiffRhythm 1.2 model", - "guidance_scale": "Controls how closely the output follows the prompt (1.0-10.0, default: 4.0)", + "model": "cfm_model_v1_2.pt (DiffRhythm 1.2 - 95s generation)", + "style_prompt": "Text description of the desired music style, mood, and instruments", + "unload_model": "Boolean to unload model after generation (default: true)", + "odeint_method": "ODE solver: euler, midpoint, rk4, implicit_adams (default: euler)", + "steps": "Number of diffusion steps: 1-100 (default: 30)", + "cfg": "Classifier-free guidance scale: 1-10 (default: 4)", + "quality_or_speed": "Generation mode: quality or speed (default: speed)", "seed": "Random seed for reproducibility (default: 42)", - "model": "cfm_model_v1_2 (DiffRhythm 1.2 - 95s generation)", - "device": "auto (automatic GPU selection)" + "edit": "Enable segment editing mode (default: false)", + "edit_segments": "Segments to edit when edit=true (default: [-1, 20], [60, -1])" }, "notes": [ "This workflow uses DiffRhythm 1.2 for 95-second music generation", - "All parameters are optional - can generate music randomly without inputs", + "All parameters except model and style_prompt are optional", "Supports English and Chinese text prompts", "Generation time: ~30-60 seconds on RTX 4090", - "PLACEHOLDER: Actual node names and parameters need to be updated after ComfyUI_DiffRhythm installation" + "Can optionally connect MultiLineLyricsDR node for lyrics input" ] } },