diff --git a/example_workflows/lightx2v_seko_talk.json b/example_workflows/lightx2v_seko_talk.json index 10277db..ca7a154 100644 --- a/example_workflows/lightx2v_seko_talk.json +++ b/example_workflows/lightx2v_seko_talk.json @@ -1,7 +1,7 @@ { "11": { "inputs": { - "audio": "12秒.mp3", + "audio": "audio_full_female_10s.wav", "start_time": 0, "duration": 0 }, @@ -25,6 +25,14 @@ "audio": [ "11", 0 + ], + "memory_config": [ + "16", + 0 + ], + "quantization_config": [ + "17", + 0 ] }, "class_type": "LightX2VConfigCombinerV2", @@ -35,7 +43,7 @@ "14": { "inputs": { "model_cls": "seko_talk", - "model_name": "SekoTalk-v2.7_beta2-bf16-step4_temp", + "model_name": "SekoTalk-v2.7-fp8-step4-xt-490", "task": "rs2v", "infer_steps": 4, "seed": 4221706066, @@ -70,23 +78,54 @@ "title": "LightX2V Modular Inference V2" } }, + "16": { + "inputs": { + "enable_rotary_chunk": false, + "rotary_chunk_size": 100, + "clean_cuda_cache": true, + "cpu_offload": true, + "offload_granularity": "block", + "offload_ratio": 1.0, + "t5_cpu_offload": true, + "t5_offload_granularity": "model", + "audio_encoder_cpu_offload": true, + "audio_adapter_cpu_offload": true, + "vae_cpu_offload": true, + "use_tiling_vae": true, + "lazy_load": false, + "unload_after_inference": false + }, + "class_type": "LightX2VMemoryOptimization", + "_meta": { + "title": "LightX2V Memory Optimization" + } + }, + "17": { + "inputs": { + "dit_quant_scheme": "fp8-sgl", + "t5_quant_scheme": "fp8-sgl", + "clip_quant_scheme": "fp8-sgl", + "adapter_quant_scheme": "fp8-sgl" + }, + "class_type": "LightX2VQuantization", + "_meta": { + "title": "LightX2V Quantization" + } + }, "18": { "inputs": { - "frame_rate": [ - "22", - 0 - ], + "frame_rate": 16, "loop_count": 0, - "filename_prefix": "vigen-15ebb023", + "filename_prefix": "lightx2v_sekotalk/single", "format": "video/h264-mp4", "pix_fmt": "yuv420p", - "crf": 23, + "crf": 19, "save_metadata": false, "trim_to_audio": false, "pingpong": false, - "save_output": false, + "save_output": true, "images": [ - "21", + "15", 0 ], "audio": [ @@ -101,41 +140,11 @@ }, "20": { "inputs": { - "image": "00000.jpg" + "image": "codex_image_20260922_135831_1323a530_B.jpg" }, "class_type": "LoadImage", "_meta": { "title": "Load Image" } - }, - "21": { - "inputs": { - "source_fps": 16, - "target_fps": [ - "22", - 0 - ], - "scale": 1, - "model_name": "flownet.pkl", - "batch_size": 8, - "use_fp16": true, - "images": [ - "15", - 0 - ] - }, - "class_type": "RIFEInterpolation", - "_meta": { - "title": "RIFE Frame Interpolation" - } - }, - "22": { - "inputs": { - "value": 25.000000000000007 - }, - "class_type": "FloatConstant", - "_meta": { - "title": "target fps" - } } -} \ No newline at end of file +} diff --git a/example_workflows/lightx2v_seko_talk_multi_talk.json b/example_workflows/lightx2v_seko_talk_multi_talk.json index 8532ab3..9d81b96 100644 --- a/example_workflows/lightx2v_seko_talk_multi_talk.json +++ b/example_workflows/lightx2v_seko_talk_multi_talk.json @@ -1,8 +1,8 @@ { "id": "00000000-0000-0000-0000-000000000000", "revision": 0, - "last_node_id": 50, - "last_link_id": 49, + "last_node_id": 51, + "last_link_id": 50, "nodes": [ { "id": 10, @@ -32,16 +32,15 @@ "Node name for S&R": "LightX2VQuantization" }, "widgets_values": [ - "sgl", - "fp8", - "fp8", - "fp16", - "fp8" + "fp8-sgl", + "fp8-sgl", + "fp8-sgl", + "fp8-sgl" ] }, { "id": 11, - "type": "LightX2VConfigCombiner", + "type": "LightX2VConfigCombinerV3", "pos": [ -1207.53271484375, 111.63562774658203 @@ -51,7 +50,7 @@ 126 ], "flags": {}, - "order": 14, + "order": 16, "mode": 0, "inputs": [ { @@ -75,7 +74,7 @@ "name": "memory_config", "shape": 7, "type": "MEMORY_CONFIG", - "link": null + "link": 50 }, { "name": "lora_chain", @@ -88,41 +87,6 @@ "shape": 7, "type": "TALK_OBJECTS_CONFIG", "link": 49 - } - ], - "outputs": [ - { - "name": "combined_config", - "type": "COMBINED_CONFIG", - "links": [ - 13 - ] - } - ], - "properties": { - "Node name for S&R": "LightX2VConfigCombiner" - }, - "widgets_values": [] - }, - { - "id": 12, - "type": "LightX2VModularInference", - "pos": [ - -818.747802734375, - 89.00883483886719 - ], - "size": [ - 400, - 200 - ], - "flags": {}, - "order": 16, - "mode": 0, - "inputs": [ - { - "name": "combined_config", - "type": "COMBINED_CONFIG", - "link": 13 }, { "name": "image", @@ -134,7 +98,42 @@ "name": "audio", "shape": 7, "type": "AUDIO", - "link": 15 + "link": null + } + ], + "outputs": [ + { + "name": "prepared_config", + "type": "PREPARED_CONFIG", + "links": [ + 13 + ] + } + ], + "properties": { + "Node name for S&R": "LightX2VConfigCombinerV3" + }, + "widgets_values": [] + }, + { + "id": 12, + "type": "LightX2VModularInferenceV2", + "pos": [ + -818.747802734375, + 89.00883483886719 + ], + "size": [ + 400, + 200 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "name": "prepared_config", + "type": "PREPARED_CONFIG", + "link": 13 } ], "outputs": [ @@ -154,7 +153,7 @@ } ], "properties": { - "Node name for S&R": "LightX2VModularInference" + "Node name for S&R": "LightX2VModularInferenceV2" }, "widgets_values": [ "The video feature the person is talking.", @@ -195,44 +194,10 @@ "Node name for S&R": "LoadImage" }, "widgets_values": [ - "input (1).png", + "codex_two_person_input.png", "image" ] }, - { - "id": 20, - "type": "LoadAudio", - "pos": [ - -1618.51171875, - 526.3804931640625 - ], - "size": [ - 274.080078125, - 136 - ], - "flags": {}, - "order": 10, - "mode": 0, - "inputs": [], - "outputs": [ - { - "name": "AUDIO", - "type": "AUDIO", - "links": [ - 15 - ] - } - ], - "title": "加载音频", - "properties": { - "Node name for S&R": "LoadAudio" - }, - "widgets_values": [ - "15.wav", - null, - null - ] - }, { "id": 21, "type": "VHS_VideoCombine", @@ -337,8 +302,8 @@ }, "widgets_values": [ "seko_talk", - "Wan2.1-R2V0909-Audio-14B-720P-fp8", - "i2v", + "SekoTalk-v2.7-fp8-step4-xt-490", + "rs2v", 4, 584734195, "randomize", @@ -357,42 +322,6 @@ false ] }, - { - "id": 34, - "type": "easy showAnything", - "pos": [ - -508.2369079589844, - -330.85296630859375 - ], - "size": [ - 511.8559875488281, - 291.96728515625 - ], - "flags": {}, - "order": 17, - "mode": 0, - "inputs": [ - { - "name": "anything", - "shape": 7, - "type": "*", - "link": 42 - } - ], - "outputs": [ - { - "name": "output", - "type": "*", - "links": [] - } - ], - "properties": { - "Node name for S&R": "easy showAnything" - }, - "widgets_values": [ - "TalkObjectsConfig(talk_objects=[{'name': 'person_1', 'audio': '/mnt/aigc/users/gaopeng1/ComfyUI/input/person_1_audio.wav', 'mask': '/mnt/aigc/users/gaopeng1/ComfyUI/input/person_1_mask.png', 'source_type': 'file'}, {'name': 'person_1', 'audio': '/mnt/aigc/users/gaopeng1/ComfyUI/input/person_1_audio.wav', 'mask': '/mnt/aigc/users/gaopeng1/ComfyUI/input/person_1_mask.png', 'source_type': 'file'}])" - ] - }, { "id": 36, "type": "LoadAudio", @@ -423,7 +352,7 @@ "Node name for S&R": "LoadAudio" }, "widgets_values": [ - "p2.mp3", + "audio_full_female_10s.wav", null, null ] @@ -458,8 +387,8 @@ "Node name for S&R": "LoadImageMask" }, "widgets_values": [ - "input_p2_mask.png", - "red", + "codex_two_person_input.png", + "blue", "image" ] }, @@ -493,77 +422,7 @@ "Node name for S&R": "LoadImageMask" }, "widgets_values": [ - "input_p1_mask.png", - "red", - "image" - ] - }, - { - "id": 41, - "type": "LoadAudio", - "pos": [ - -1468.0582275390625, - -386.4920654296875 - ], - "size": [ - 274.080078125, - 136 - ], - "flags": { - "collapsed": true - }, - "order": 4, - "mode": 0, - "inputs": [], - "outputs": [ - { - "name": "AUDIO", - "type": "AUDIO", - "links": [ - 44 - ] - } - ], - "properties": { - "Node name for S&R": "LoadAudio" - }, - "widgets_values": [ - "15.wav", - null, - null - ] - }, - { - "id": 42, - "type": "LoadImageMask", - "pos": [ - -1477.0850830078125, - -332.2462463378906 - ], - "size": [ - 274.080078125, - 318 - ], - "flags": { - "collapsed": false - }, - "order": 3, - "mode": 0, - "inputs": [], - "outputs": [ - { - "name": "MASK", - "type": "MASK", - "links": [ - 45 - ] - } - ], - "properties": { - "Node name for S&R": "LoadImageMask" - }, - "widgets_values": [ - "input_p3_mask.png", + "codex_two_person_input.png", "red", "image" ] @@ -649,8 +508,7 @@ "name": "talk_objects_config", "type": "TALK_OBJECTS_CONFIG", "links": [ - 42, - 48 + 49 ] } ], @@ -744,50 +602,7 @@ "Node name for S&R": "LightX2VTalkObjectInput" }, "widgets_values": [ - "person_1", - true - ] - }, - { - "id": 46, - "type": "LightX2VTalkObjectInput", - "pos": [ - -937.0840454101562, - -414.41925048828125 - ], - "size": [ - 317.0162048339844, - 102 - ], - "flags": {}, - "order": 12, - "mode": 0, - "inputs": [ - { - "name": "audio", - "shape": 7, - "type": "AUDIO", - "link": 44 - }, - { - "name": "mask", - "shape": 7, - "type": "MASK", - "link": 45 - } - ], - "outputs": [ - { - "name": "talk_object", - "type": "TALK_OBJECT", - "links": [] - } - ], - "properties": { - "Node name for S&R": "LightX2VTalkObjectInput" - }, - "widgets_values": [ - "person_1", + "person_2", true ] }, @@ -821,59 +636,21 @@ "Node name for S&R": "LoadAudio" }, "widgets_values": [ - "p1.mp3", + "male_10s.wav", null, "" ] }, { - "id": 48, - "type": "SetNode", + "id": 51, + "type": "LightX2VMemoryOptimization", "pos": [ - -199.871337890625, - -578.7578735351562 + -1750, + 420 ], "size": [ - 210, - 60 - ], - "flags": {}, - "order": 18, - "mode": 0, - "inputs": [ - { - "name": "TALK_OBJECTS_CONFIG", - "type": "TALK_OBJECTS_CONFIG", - "link": 48 - } - ], - "outputs": [ - { - "name": "*", - "type": "*", - "links": null - } - ], - "title": "Set_talk_objects", - "properties": { - "previousName": "talk_objects" - }, - "widgets_values": [ - "talk_objects" - ], - "color": "#232", - "bgcolor": "#353" - }, - { - "id": 50, - "type": "GetNode", - "pos": [ - -1453.525390625, - 249.66848754882812 - ], - "size": [ - 210, - 60 + 290, + 420 ], "flags": {}, "order": 7, @@ -881,20 +658,32 @@ "inputs": [], "outputs": [ { - "name": "TALK_OBJECTS_CONFIG", - "type": "TALK_OBJECTS_CONFIG", + "name": "memory_config", + "type": "MEMORY_CONFIG", "links": [ - 49 + 50 ] } ], - "title": "Get_talk_objects", - "properties": {}, + "properties": { + "Node name for S&R": "LightX2VMemoryOptimization" + }, "widgets_values": [ - "talk_objects" - ], - "color": "#232", - "bgcolor": "#353" + false, + 100, + true, + true, + "block", + 1.0, + true, + "model", + true, + true, + true, + true, + false, + false + ] } ], "links": [ @@ -920,24 +709,16 @@ 0, 12, 0, - "COMBINED_CONFIG" + "PREPARED_CONFIG" ], [ 14, 19, 0, - 12, - 1, + 11, + 6, "IMAGE" ], - [ - 15, - 20, - 0, - 12, - 2, - "AUDIO" - ], [ 18, 12, @@ -994,30 +775,6 @@ 1, "TALK_OBJECT" ], - [ - 42, - 43, - 0, - 34, - 0, - "*" - ], - [ - 44, - 41, - 0, - 46, - 0, - "AUDIO" - ], - [ - 45, - 42, - 0, - 46, - 1, - "MASK" - ], [ 47, 47, @@ -1026,21 +783,21 @@ 0, "AUDIO" ], - [ - 48, - 43, - 0, - 48, - 0, - "*" - ], [ 49, - 50, + 43, 0, 11, 5, "TALK_OBJECTS_CONFIG" + ], + [ + 50, + 51, + 0, + 11, + 3, + "MEMORY_CONFIG" ] ], "groups": [