diff --git a/example_workflows/hyvideo_i2v_example_01.json b/example_workflows/hyvideo_i2v_example_01.json new file mode 100644 index 0000000..57cbaf8 --- /dev/null +++ b/example_workflows/hyvideo_i2v_example_01.json @@ -0,0 +1,1388 @@ +{ + "last_node_id": 96, + "last_link_id": 178, + "nodes": [ + { + "id": 5, + "type": "HyVideoDecode", + "pos": [ + 641.3367919921875, + -277.4842834472656 + ], + "size": [ + 345.4285888671875, + 150 + ], + "flags": {}, + "order": 24, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "VAE", + "link": 175 + }, + { + "name": "samples", + "type": "LATENT", + "link": 167 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 134 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "HyVideoDecode" + }, + "widgets_values": [ + true, + 64, + 192, + false + ] + }, + { + "id": 70, + "type": "Note", + "pos": [ + 272.005615234375, + -623.9506225585938 + ], + "size": [ + 299.13330078125, + 88 + ], + "flags": {}, + "order": 0, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Enhance a video weight should be relative to the video lenght, if you get noisy results it's too strong" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 91, + "type": "HyVideoEnhanceAVideo", + "pos": [ + 256.133056640625, + -481.41058349609375 + ], + "size": [ + 352.79998779296875, + 154 + ], + "flags": {}, + "order": 1, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "feta_args", + "type": "FETAARGS", + "links": [] + } + ], + "properties": { + "Node name for S&R": "HyVideoEnhanceAVideo" + }, + "widgets_values": [ + 2, + true, + true, + 0, + 1 + ] + }, + { + "id": 85, + "type": "GetImageSizeAndCount", + "pos": [ + 712.0123291015625, + -66.81350708007812 + ], + "size": [ + 277.20001220703125, + 86 + ], + "flags": {}, + "order": 25, + "mode": 0, + "inputs": [ + { + "name": "image", + "type": "IMAGE", + "link": 134 + } + ], + "outputs": [ + { + "name": "image", + "type": "IMAGE", + "links": [ + 135 + ], + "slot_index": 0 + }, + { + "name": "512 width", + "type": "INT", + "links": null + }, + { + "name": "512 height", + "type": "INT", + "links": null + }, + { + "name": "113 count", + "type": "INT", + "links": null + } + ], + "properties": { + "Node name for S&R": "GetImageSizeAndCount" + }, + "widgets_values": [] + }, + { + "id": 57, + "type": "HyVideoTorchCompileSettings", + "pos": [ + -1440, + -920 + ], + "size": [ + 441, + 274 + ], + "flags": {}, + "order": 2, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "torch_compile_args", + "type": "COMPILEARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "HyVideoTorchCompileSettings" + }, + "widgets_values": [ + "inductor", + false, + "default", + false, + 64, + true, + true, + false, + false, + false + ] + }, + { + "id": 61, + "type": "Note", + "pos": [ + -1434.390625, + -1056.519775390625 + ], + "size": [ + 258.9027099609375, + 88 + ], + "flags": {}, + "order": 3, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "If you have working Triton install, torch compile will reduce VRAM use and increase speed about 30%" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 63, + "type": "Note", + "pos": [ + -913.1675415039062, + -852.4307250976562 + ], + "size": [ + 329.93341064453125, + 88 + ], + "flags": {}, + "order": 4, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "https://huggingface.co/Kijai/HunyuanVideo_comfy/blob/main/hunyuan_video_vae_bf16.safetensors" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 16, + "type": "DownloadAndLoadHyVideoTextEncoder", + "pos": [ + -945.616943359375, + -120.7367935180664 + ], + "size": [ + 441, + 202 + ], + "flags": {}, + "order": 5, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "hyvid_text_encoder", + "type": "HYVIDTEXTENCODER", + "links": [ + 114 + ] + } + ], + "properties": { + "Node name for S&R": "DownloadAndLoadHyVideoTextEncoder" + }, + "widgets_values": [ + "xtuner/llava-llama-3-8b-v1_1-transformers", + "openai/clip-vit-large-patch14", + "fp16", + false, + 2, + "disabled", + "offload_device" + ] + }, + { + "id": 87, + "type": "GetImageSizeAndCount", + "pos": [ + -704.3087158203125, + 477.6371765136719 + ], + "size": [ + 277.20001220703125, + 86 + ], + "flags": {}, + "order": 19, + "mode": 0, + "inputs": [ + { + "name": "image", + "type": "IMAGE", + "link": 161 + } + ], + "outputs": [ + { + "name": "image", + "type": "IMAGE", + "links": [ + 144, + 145 + ], + "slot_index": 0 + }, + { + "name": "512 width", + "type": "INT", + "links": [ + 169 + ], + "slot_index": 1 + }, + { + "name": "512 height", + "type": "INT", + "links": [ + 170 + ], + "slot_index": 2 + }, + { + "name": "1 count", + "type": "INT", + "links": null + } + ], + "properties": { + "Node name for S&R": "GetImageSizeAndCount" + }, + "widgets_values": [] + }, + { + "id": 89, + "type": "ImageScale", + "pos": [ + -1059.9942626953125, + 478.9391174316406 + ], + "size": [ + 315, + 170 + ], + "flags": {}, + "order": 18, + "mode": 0, + "inputs": [ + { + "name": "image", + "type": "IMAGE", + "link": 160 + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 158 + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 159 + } + ], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 161, + 172 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "ImageScale" + }, + "widgets_values": [ + "lanczos", + 512, + 512, + "disabled" + ] + }, + { + "id": 92, + "type": "SetNode", + "pos": [ + -700.1900634765625, + 415.1511535644531 + ], + "size": [ + 210, + 60 + ], + "flags": { + "collapsed": true + }, + "order": 20, + "mode": 0, + "inputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "link": 172 + } + ], + "outputs": [ + { + "name": "*", + "type": "*", + "links": null + } + ], + "title": "Set_InputImage", + "properties": { + "previousName": "InputImage" + }, + "widgets_values": [ + "InputImage" + ], + "color": "#2a363b", + "bgcolor": "#3f5159" + }, + { + "id": 93, + "type": "GetNode", + "pos": [ + 810, + 100 + ], + "size": [ + 210, + 60 + ], + "flags": { + "collapsed": true + }, + "order": 6, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 173 + ], + "slot_index": 0 + } + ], + "title": "Get_InputImage", + "properties": {}, + "widgets_values": [ + "InputImage" + ], + "color": "#2a363b", + "bgcolor": "#3f5159" + }, + { + "id": 52, + "type": "ImageConcatMulti", + "pos": [ + 790, + 150 + ], + "size": [ + 210, + 150 + ], + "flags": {}, + "order": 26, + "mode": 0, + "inputs": [ + { + "name": "image_1", + "type": "IMAGE", + "link": 173 + }, + { + "name": "image_2", + "type": "IMAGE", + "link": 135 + } + ], + "outputs": [ + { + "name": "images", + "type": "IMAGE", + "links": [ + 133 + ], + "slot_index": 0 + } + ], + "properties": {}, + "widgets_values": [ + 2, + "right", + false, + null + ] + }, + { + "id": 94, + "type": "Reroute", + "pos": [ + -325.2616271972656, + -281.5520935058594 + ], + "size": [ + 75, + 26 + ], + "flags": {}, + "order": 17, + "mode": 0, + "inputs": [ + { + "name": "", + "type": "*", + "link": 174 + } + ], + "outputs": [ + { + "name": "", + "type": "VAE", + "links": [ + 175, + 176 + ], + "slot_index": 0 + } + ], + "properties": { + "showOutputText": false, + "horizontal": false + } + }, + { + "id": 59, + "type": "HyVideoBlockSwap", + "pos": [ + -1358.3192138671875, + -432.2845764160156 + ], + "size": [ + 315, + 130 + ], + "flags": {}, + "order": 7, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "links": [], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "HyVideoBlockSwap" + }, + "widgets_values": [ + 20, + 0, + false, + false + ] + }, + { + "id": 69, + "type": "Note", + "pos": [ + -1338.4915771484375, + -570.17236328125 + ], + "size": [ + 275.66656494140625, + 88 + ], + "flags": {}, + "order": 8, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "block swap is a manual way to do cpu offloading, use this to trade speed with memory use" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 72, + "type": "LoadImage", + "pos": [ + -1568.572265625, + 173.88914489746094 + ], + "size": [ + 456.52972412109375, + 499.45269775390625 + ], + "flags": {}, + "order": 9, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "IMAGE", + "type": "IMAGE", + "links": [ + 128, + 160 + ], + "slot_index": 0 + }, + { + "name": "MASK", + "type": "MASK", + "links": null + } + ], + "properties": { + "Node name for S&R": "LoadImage" + }, + "widgets_values": [ + "anya.jpg", + "image" + ] + }, + { + "id": 77, + "type": "HyVideoI2VEncode", + "pos": [ + -238.79173278808594, + 145.7522430419922 + ], + "size": [ + 434.1623840332031, + 253.68370056152344 + ], + "flags": {}, + "order": 22, + "mode": 0, + "inputs": [ + { + "name": "text_encoders", + "type": "HYVIDTEXTENCODER", + "link": 114 + }, + { + "name": "clip_l", + "type": "CLIP", + "shape": 7, + "link": null + }, + { + "name": "image", + "type": "IMAGE", + "shape": 7, + "link": 145 + }, + { + "name": "hyvid_cfg", + "type": "HYVID_CFG", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "hyvid_embeds", + "type": "HYVIDEMBEDS", + "links": [ + 163 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "HyVideoI2VEncode" + }, + "widgets_values": [ + "chibi figurine dances", + true, + "I2V_video" + ] + }, + { + "id": 43, + "type": "HyVideoEncode", + "pos": [ + -236.47976684570312, + -114.70182800292969 + ], + "size": [ + 315, + 198 + ], + "flags": {}, + "order": 21, + "mode": 0, + "inputs": [ + { + "name": "vae", + "type": "VAE", + "link": 176 + }, + { + "name": "image", + "type": "IMAGE", + "link": 144 + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 164 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "HyVideoEncode" + }, + "widgets_values": [ + false, + 64, + 256, + true, + 0.020000000000000004, + 1 + ] + }, + { + "id": 95, + "type": "HyVideoTeaCache", + "pos": [ + -123.18978881835938, + -441.425537109375 + ], + "size": [ + 315, + 58 + ], + "flags": {}, + "order": 10, + "mode": 0, + "inputs": [], + "outputs": [ + { + "name": "teacache_args", + "type": "TEACACHEARGS", + "links": [ + 178 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "HyVideoTeaCache" + }, + "widgets_values": [ + 0.15000000000000002 + ] + }, + { + "id": 62, + "type": "Note", + "pos": [ + -940.7366333007812, + -561.2342529296875 + ], + "size": [ + 393.7334289550781, + 88 + ], + "flags": {}, + "order": 11, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "https://huggingface.co/Kijai/HunyuanVideo_comfy/blob/main/hunyuan_video_I2V_fp8_e4m3fn.safetensors" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 7, + "type": "HyVideoVAELoader", + "pos": [ + -930, + -710 + ], + "size": [ + 379.166748046875, + 82 + ], + "flags": {}, + "order": 12, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "COMPILEARGS", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "vae", + "type": "VAE", + "links": [ + 174 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "HyVideoVAELoader" + }, + "widgets_values": [ + "hyvid\\hunyuan_video_vae_bf16.safetensors", + "fp32" + ] + }, + { + "id": 73, + "type": "HyVideoGetClosestBucketSize", + "pos": [ + -1055.0694580078125, + 348.167724609375 + ], + "size": [ + 302.3999938964844, + 78 + ], + "flags": {}, + "order": 16, + "mode": 0, + "inputs": [ + { + "name": "image", + "type": "IMAGE", + "link": 128 + } + ], + "outputs": [ + { + "name": "width", + "type": "INT", + "links": [ + 158 + ], + "slot_index": 0 + }, + { + "name": "height", + "type": "INT", + "links": [ + 159 + ], + "slot_index": 1 + } + ], + "properties": { + "Node name for S&R": "HyVideoGetClosestBucketSize" + }, + "widgets_values": [ + "540" + ] + }, + { + "id": 71, + "type": "Note", + "pos": [ + -1250, + -220 + ], + "size": [ + 275.66656494140625, + 88 + ], + "flags": {}, + "order": 13, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "Use sageattention if you can, flash attention if you can't... last resort use sdpa" + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 96, + "type": "Note", + "pos": [ + -1042.654296875, + 202.5398712158203 + ], + "size": [ + 275.66656494140625, + 88 + ], + "flags": {}, + "order": 14, + "mode": 0, + "inputs": [], + "outputs": [], + "properties": {}, + "widgets_values": [ + "You don't have to use these sizes, it's just what the original pipeline used for reference." + ], + "color": "#432", + "bgcolor": "#653" + }, + { + "id": 84, + "type": "VHS_VideoCombine", + "pos": [ + 1070.051513671875, + -287.26409912109375 + ], + "size": [ + 662.8809204101562, + 669.4404296875 + ], + "flags": {}, + "order": 27, + "mode": 0, + "inputs": [ + { + "name": "images", + "type": "IMAGE", + "link": 133 + }, + { + "name": "audio", + "type": "AUDIO", + "shape": 7, + "link": null + }, + { + "name": "meta_batch", + "type": "VHS_BatchManager", + "shape": 7, + "link": null + }, + { + "name": "vae", + "type": "VAE", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "Filenames", + "type": "VHS_FILENAMES", + "links": null + } + ], + "properties": { + "Node name for S&R": "VHS_VideoCombine" + }, + "widgets_values": { + "frame_rate": 24, + "loop_count": 0, + "filename_prefix": "HunyuanVideoWrapper_I2V", + "format": "video/h264-mp4", + "pix_fmt": "yuv420p", + "crf": 19, + "save_metadata": true, + "trim_to_audio": false, + "pingpong": false, + "save_output": true, + "videopreview": { + "hidden": false, + "paused": false, + "params": { + "filename": "HunyuanVideoWrapper_I2V_00002.mp4", + "subfolder": "", + "type": "output", + "format": "video/h264-mp4", + "frame_rate": 24, + "workflow": "HunyuanVideoWrapper_I2V_00002.png", + "fullpath": "N:\\AI\\ComfyUI\\output\\HunyuanVideoWrapper_I2V_00002.mp4" + }, + "muted": false + } + } + }, + { + "id": 90, + "type": "HyVideoSampler", + "pos": [ + 259.2420349121094, + -197.0081024169922 + ], + "size": [ + 339.4956970214844, + 835.4957275390625 + ], + "flags": {}, + "order": 23, + "mode": 0, + "inputs": [ + { + "name": "model", + "type": "HYVIDEOMODEL", + "link": 162 + }, + { + "name": "hyvid_embeds", + "type": "HYVIDEMBEDS", + "link": 163 + }, + { + "name": "samples", + "type": "LATENT", + "shape": 7, + "link": null + }, + { + "name": "image_cond_latents", + "type": "LATENT", + "shape": 7, + "link": 164 + }, + { + "name": "stg_args", + "type": "STGARGS", + "shape": 7, + "link": null + }, + { + "name": "context_options", + "type": "HYVIDCONTEXT", + "shape": 7, + "link": null + }, + { + "name": "feta_args", + "type": "FETAARGS", + "shape": 7, + "link": null + }, + { + "name": "teacache_args", + "type": "TEACACHEARGS", + "shape": 7, + "link": 178 + }, + { + "name": "width", + "type": "INT", + "widget": { + "name": "width" + }, + "link": 169 + }, + { + "name": "height", + "type": "INT", + "widget": { + "name": "height" + }, + "link": 170 + } + ], + "outputs": [ + { + "name": "samples", + "type": "LATENT", + "links": [ + 167 + ] + } + ], + "properties": { + "Node name for S&R": "HyVideoSampler" + }, + "widgets_values": [ + 512, + 512, + 129, + 30, + 6, + 17.000000000000004, + 128, + "fixed", + true, + 1, + "FlowMatchDiscreteScheduler", + 0, + "" + ] + }, + { + "id": 1, + "type": "HyVideoModelLoader", + "pos": [ + -950, + -420 + ], + "size": [ + 426.1773986816406, + 242 + ], + "flags": {}, + "order": 15, + "mode": 0, + "inputs": [ + { + "name": "compile_args", + "type": "COMPILEARGS", + "shape": 7, + "link": null + }, + { + "name": "block_swap_args", + "type": "BLOCKSWAPARGS", + "shape": 7, + "link": null + }, + { + "name": "lora", + "type": "HYVIDLORA", + "shape": 7, + "link": null + } + ], + "outputs": [ + { + "name": "model", + "type": "HYVIDEOMODEL", + "links": [ + 162 + ], + "slot_index": 0 + } + ], + "properties": { + "Node name for S&R": "HyVideoModelLoader" + }, + "widgets_values": [ + "hyvideo\\hunyuan_video_I2V_fp8_e4m3fn.safetensors", + "bf16", + "fp8_e4m3fn", + "offload_device", + "sageattn_varlen", + false, + true + ] + } + ], + "links": [ + [ + 114, + 16, + 0, + 77, + 0, + "HYVIDTEXTENCODER" + ], + [ + 128, + 72, + 0, + 73, + 0, + "IMAGE" + ], + [ + 133, + 52, + 0, + 84, + 0, + "IMAGE" + ], + [ + 134, + 5, + 0, + 85, + 0, + "IMAGE" + ], + [ + 135, + 85, + 0, + 52, + 1, + "IMAGE" + ], + [ + 144, + 87, + 0, + 43, + 1, + "IMAGE" + ], + [ + 145, + 87, + 0, + 77, + 2, + "IMAGE" + ], + [ + 158, + 73, + 0, + 89, + 1, + "INT" + ], + [ + 159, + 73, + 1, + 89, + 2, + "INT" + ], + [ + 160, + 72, + 0, + 89, + 0, + "IMAGE" + ], + [ + 161, + 89, + 0, + 87, + 0, + "IMAGE" + ], + [ + 162, + 1, + 0, + 90, + 0, + "HYVIDEOMODEL" + ], + [ + 163, + 77, + 0, + 90, + 1, + "HYVIDEMBEDS" + ], + [ + 164, + 43, + 0, + 90, + 3, + "LATENT" + ], + [ + 167, + 90, + 0, + 5, + 1, + "LATENT" + ], + [ + 169, + 87, + 1, + 90, + 8, + "INT" + ], + [ + 170, + 87, + 2, + 90, + 9, + "INT" + ], + [ + 172, + 89, + 0, + 92, + 0, + "IMAGE" + ], + [ + 173, + 93, + 0, + 52, + 0, + "IMAGE" + ], + [ + 174, + 7, + 0, + 94, + 0, + "*" + ], + [ + 175, + 94, + 0, + 5, + 0, + "VAE" + ], + [ + 176, + 94, + 0, + 43, + 0, + "VAE" + ], + [ + 178, + 95, + 0, + 90, + 7, + "TEACACHEARGS" + ] + ], + "groups": [], + "config": {}, + "extra": { + "ds": { + "scale": 0.672749994932602, + "offset": [ + 1809.9348428723306, + 884.5107343698774 + ] + }, + "node_versions": { + "ComfyUI-HunyuanVideoWrapper": "22d5225e357404de9602d4d0a08949676bc37360", + "ComfyUI-KJNodes": "fa6d20eeb32cbcbd84ee325e3cfdc6ed6b43056f", + "comfy-core": "0.3.19", + "ComfyUI-VideoHelperSuite": "2c25b8b53835aaeb63f831b3137c705cf9f85dce" + }, + "VHS_latentpreview": true, + "VHS_latentpreviewrate": 0, + "VHS_MetadataImage": true, + "VHS_KeepIntermediate": true + }, + "version": 0.4 +} \ No newline at end of file