hanzoui/workflow-templates-broken-zap-2026-06-08
1
0
Fork 0
mirror of https://github.com/hanzoui/workflow-templates-broken-zap-2026-06-08.git synced 2026-10-30 20:44:35 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
main
workflow-templates-broken-z…/templates/video_humo.json
T
zeekay 006e96e64a feat: templates batch 15
2026-06-07 20:55:09 -07:00

1078 lines
21 KiB
JSON
Raw Permalink Blame History

{
"id": "428ebf59-f870-43e5-b3a9-ad0c0b7b33f4",
"revision": 2,
"last_node_id": 75,
"last_link_id": 147,
"nodes": [
{
"id": 38,
"type": "CLIPLoader",
"pos": [
-50,
208
],
"size": [
390,
106
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"slot_index": 0,
"links": [
74,
75
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "CLIPLoader",
"models": [
{
"name": "umt5_xxl_fp8_e4m3fn_scaled.safetensors",
"url": "https://huggingface.co/hanzoui/Wan_2.1_HanzoStudio_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors",
"directory": "text_encoders"
}
]
},
"widgets_values": [
"umt5_xxl_fp8_e4m3fn_scaled.safetensors",
"wan",
"default"
]
},
{
"id": 39,
"type": "VAELoader",
"pos": [
-50,
356
],
"size": [
390,
58
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "VAE",
"type": "VAE",
"slot_index": 0,
"links": [
136,
137
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "VAELoader",
"models": [
{
"name": "wan_2.1_vae.safetensors",
"url": "https://huggingface.co/hanzoui/Wan_2.2_HanzoStudio_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors",
"directory": "vae"
}
]
},
"widgets_values": [
"wan_2.1_vae.safetensors"
]
},
{
"id": 60,
"type": "CreateVideo",
"pos": [
850,
650
],
"size": [
230,
80
],
"flags": {},
"order": 18,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 143
},
{
"name": "audio",
"shape": 7,
"type": "AUDIO",
"link": 120
}
],
"outputs": [
{
"name": "VIDEO",
"type": "VIDEO",
"links": [
119
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "CreateVideo"
},
"widgets_values": [
25
]
},
{
"id": 63,
"type": "VAEDecode",
"pos": [
850,
560
],
"size": [
140,
46
],
"flags": {},
"order": 17,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 132
},
{
"name": "vae",
"type": "VAE",
"link": 136
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"slot_index": 0,
"links": [
143
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "VAEDecode"
},
"widgets_values": []
},
{
"id": 61,
"type": "LoraLoaderModelOnly",
"pos": [
-50,
84
],
"size": [
390,
82
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 122
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
124
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "LoraLoaderModelOnly",
"models": [
{
"name": "lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors",
"url": "https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors",
"directory": "loras"
}
]
},
"widgets_values": [
"lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors",
1
]
},
{
"id": 37,
"type": "UNETLoader",
"pos": [
-50,
-40
],
"size": [
390,
82
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"slot_index": 0,
"links": [
122
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "UNETLoader",
"models": [
{
"name": "humo_17B_fp8_e4m3fn.safetensors",
"url": "https://huggingface.co/hanzoui/HuMo_HanzoStudio/resolve/main/split_files/diffusion_models/humo_17B_fp8_e4m3fn.safetensors",
"directory": "diffusion_models"
}
]
},
"widgets_values": [
"humo_17B_fp8_e4m3fn.safetensors",
"default"
]
},
{
"id": 65,
"type": "WanHuMoImageToVideo",
"pos": [
850,
-30
],
"size": [
270,
210
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [
{
"name": "positive",
"type": "CONDITIONING",
"link": 139
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 140
},
{
"name": "vae",
"type": "VAE",
"link": 137
},
{
"name": "audio_encoder_output",
"shape": 7,
"type": "AUDIO_ENCODER_OUTPUT",
"link": 141
},
{
"name": "ref_image",
"shape": 7,
"type": "IMAGE",
"link": 142
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
133
]
},
{
"name": "negative",
"type": "CONDITIONING",
"links": [
134
]
},
{
"name": "latent",
"type": "LATENT",
"links": [
135
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "WanHuMoImageToVideo"
},
"widgets_values": [
640,
640,
97,
1
]
},
{
"id": 56,
"type": "AudioEncoderEncode",
"pos": [
850,
780
],
"size": [
285.087890625,
60
],
"flags": {
"collapsed": false
},
"order": 13,
"mode": 0,
"inputs": [
{
"name": "audio_encoder",
"type": "AUDIO_ENCODER",
"link": 115
},
{
"name": "audio",
"type": "AUDIO",
"link": 147
}
],
"outputs": [
{
"name": "AUDIO_ENCODER_OUTPUT",
"type": "AUDIO_ENCODER_OUTPUT",
"links": [
141
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "AudioEncoderEncode"
},
"widgets_values": []
},
{
"id": 57,
"type": "AudioEncoderLoader",
"pos": [
-50,
456
],
"size": [
390,
60
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO_ENCODER",
"type": "AUDIO_ENCODER",
"links": [
115
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "AudioEncoderLoader",
"models": [
{
"name": "whisper_large_v3_fp16.safetensors",
"url": "https://huggingface.co/hanzoui/HuMo_HanzoStudio/resolve/main/split_files/audio_encoders/whisper_large_v3_fp16.safetensors",
"directory": "audio_encoders"
}
]
},
"widgets_values": [
"whisper_large_v3_fp16.safetensors"
]
},
{
"id": 66,
"type": "MarkdownNote",
"pos": [
-590,
70
],
"size": [
500,
490
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [],
"title": "Note: Model links",
"properties": {},
"widgets_values": [
"\n## Model links\n\n\n**diffusion_models**\n\n- [humo_17B_fp8_e4m3fn.safetensors](https://huggingface.co/hanzoui/HuMo_HanzoStudio/resolve/main/split_files/diffusion_models/humo_17B_fp8_e4m3fn.safetensors)\n\n**loras**\n- [lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors](https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors)\n\n**text_encoders**\n- [umt5_xxl_fp8_e4m3fn_scaled.safetensors](https://huggingface.co/hanzoui/Wan_2.1_HanzoStudio_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)\n\n**vae**\n- [wan_2.1_vae.safetensors](https://huggingface.co/hanzoui/Wan_2.2_HanzoStudio_Repackaged/resolve/main/split_files/vae/wan_2.1_vae.safetensors)\n\n**audio_encoders**\n- [whisper_large_v3_fp16.safetensors](https://huggingface.co/hanzoui/HuMo_HanzoStudio/resolve/main/split_files/audio_encoders/whisper_large_v3_fp16.safetensors)\n\n\n```\n📂 HanzoStudio/\n├─ 📂 models/\n│ ├─ 📂 diffusion_models/\n│ │ └── humo_17B_fp8_e4m3fn.safetensors\n│ ├─ 📂 text_encoders/\n│ │ └── umt5_xxl_fp8_e4m3fn_scaled.safetensors \n│ ├─ 📂 audio_encoders/\n│ │ └── whisper_large_v3_fp16.safetensors \n│ └─ 📂 vae/\n│ └── wan_2.1_vae.safetensors\n```\n"
],
"color": "#432",
"bgcolor": "#000"
},
{
"id": 6,
"type": "CLIPTextEncode",
"pos": [
380,
60
],
"size": [
420,
220
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 74
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"slot_index": 0,
"links": [
139
]
}
],
"title": "CLIP Text Encode (Positive Prompt)",
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"A young boy in sci-fi style clothing is talking to the camera in an alien desert."
],
"color": "#232",
"bgcolor": "#353"
},
{
"id": 64,
"type": "KSampler",
"pos": [
840,
250
],
"size": [
270,
474
],
"flags": {},
"order": 16,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 138
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 133
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 134
},
{
"name": "latent_image",
"type": "LATENT",
"link": 135
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"slot_index": 0,
"links": [
132
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "KSampler"
},
"widgets_values": [
1067760026265042,
"randomize",
6,
1,
"uni_pc",
"simple",
1
]
},
{
"id": 48,
"type": "ModelSamplingSD3",
"pos": [
420,
-90
],
"size": [
280,
58
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 124
}
],
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"slot_index": 0,
"links": [
138
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "ModelSamplingSD3"
},
"widgets_values": [
8
]
},
{
"id": 67,
"type": "MarkdownNote",
"pos": [
-590,
-90
],
"size": [
500,
120
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [],
"title": "Note: About HuMo",
"properties": {},
"widgets_values": [
"HuMo is a human-centric video generation tool that creates controllable, high-quality human videos from multimodal inputs (text, images, audio), supporting text-image guided customization, text-audio driven audio-motion sync, and 480P(832x480)/720P(1280x720) resolutions.\n"
],
"color": "#432",
"bgcolor": "#000"
},
{
"id": 75,
"type": "MarkdownNote",
"pos": [
380,
1020
],
"size": [
430,
100
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [],
"outputs": [],
"title": "Note: About HuMo",
"properties": {},
"widgets_values": [
"If you want to use your recorded audio, please connect the audio output to the nodes that were previously linked to the LoadAudio node."
],
"color": "#432",
"bgcolor": "#000"
},
{
"id": 7,
"type": "CLIPTextEncode",
"pos": [
380,
320
],
"size": [
425.27801513671875,
180.6060791015625
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 75
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"slot_index": 0,
"links": [
140
]
}
],
"title": "CLIP Text Encode (Negative Prompt)",
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"色调艳丽，过曝，静态，细节模糊不清，字幕，风格，作品，画作，画面，静止，整体发灰，最差质量，低质量，JPEG压缩残留，丑陋的，残缺的，多余的手指，画得不好的手部，画得不好的脸部，畸形的，毁容的，形态畸形的肢体，手指融合，静止不动的画面，杂乱的背景，三条腿，背景人很多，倒着走"
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 59,
"type": "SaveVideo",
"pos": [
1150,
-80
],
"size": [
1070,
1168
],
"flags": {},
"order": 19,
"mode": 0,
"inputs": [
{
"name": "video",
"type": "VIDEO",
"link": 119
}
],
"outputs": [],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "SaveVideo"
},
"widgets_values": [
"video/HanzoStudio",
"auto",
"auto"
]
},
{
"id": 68,
"type": "RecordAudio",
"pos": [
440,
830
],
"size": [
270,
112
],
"flags": {},
"order": 7,
"mode": 4,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": []
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "RecordAudio"
},
"widgets_values": [
"",
""
]
},
{
"id": 49,
"type": "LoadImage",
"pos": [
10,
640
],
"size": [
274.080078125,
314.00006103515625
],
"flags": {},
"order": 8,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
142
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"video_humo_reference_image.png",
"image"
]
},
{
"id": 58,
"type": "LoadAudio",
"pos": [
430,
640
],
"size": [
285.087890625,
136
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
120,
147
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.3.59",
"Node name for S&R": "LoadAudio"
},
"widgets_values": [
"video_humo_input_audio.wav",
null,
null
]
}
],
"links": [
[
74,
38,
0,
6,
0,
"CLIP"
],
[
75,
38,
0,
7,
0,
"CLIP"
],
[
115,
57,
0,
56,
0,
"AUDIO_ENCODER"
],
[
119,
60,
0,
59,
0,
"VIDEO"
],
[
120,
58,
0,
60,
1,
"AUDIO"
],
[
122,
37,
0,
61,
0,
"MODEL"
],
[
124,
61,
0,
48,
0,
"MODEL"
],
[
132,
64,
0,
63,
0,
"LATENT"
],
[
133,
65,
0,
64,
1,
"CONDITIONING"
],
[
134,
65,
1,
64,
2,
"CONDITIONING"
],
[
135,
65,
2,
64,
3,
"LATENT"
],
[
136,
39,
0,
63,
1,
"VAE"
],
[
137,
39,
0,
65,
2,
"VAE"
],
[
138,
48,
0,
64,
0,
"MODEL"
],
[
139,
6,
0,
65,
0,
"CONDITIONING"
],
[
140,
7,
0,
65,
1,
"CONDITIONING"
],
[
141,
56,
0,
65,
3,
"AUDIO_ENCODER_OUTPUT"
],
[
142,
49,
0,
65,
4,
"IMAGE"
],
[
143,
63,
0,
60,
0,
"IMAGE"
],
[
147,
58,
0,
56,
1,
"AUDIO"
]
],
"groups": [
{
"id": 1,
"title": "Step 1 - Load models",
"bounding": [
-70,
-120,
430,
660
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
},
{
"id": 2,
"title": "Step 4 - Prompt",
"bounding": [
370,
-10,
450,
550
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
},
{
"id": 3,
"title": "Step 3 - Upload or record audio",
"bounding": [
370,
550,
450,
420
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
},
{
"id": 4,
"title": "Step2 - Upload reference image",
"bounding": [
-70,
550,
430,
420
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
},
{
"id": 5,
"title": "Step 5 - Video size",
"bounding": [
840,
-100,
290,
293.6000061035156
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
}
],
"config": {},
"extra": {
"ds": {
"scale": 0.5024794688220987,
"offset": [
748.712585289151,
452.86254113586153
]
},
"frontendVersion": "1.27.10",
"VHS_latentpreview": false,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"version": 0.4
}
Reference in New Issue View Git Blame Copy Permalink