Files
kijai-ComfyUI-WanVideoWrapper/example_workflows/wanvideo_480p_I2V_example_02.json
T

1258 lines
25 KiB
JSON

{
"last_node_id": 62,
"last_link_id": 64,
"nodes": [
{
"id": 46,
"type": "WanVideoTextEmbedBridge",
"pos": [
1204.152587890625,
707.1484985351562
],
"size": [
315,
46
],
"flags": {},
"order": 25,
"mode": 2,
"inputs": [
{
"name": "positive",
"type": "CONDITIONING",
"link": 54
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 55
}
],
"outputs": [
{
"name": "text_embeds",
"type": "WANVIDEOTEXTEMBEDS",
"links": null
}
],
"properties": {
"Node name for S&R": "WanVideoTextEmbedBridge"
},
"widgets_values": []
},
{
"id": 50,
"type": "CLIPTextEncode",
"pos": [
754.153076171875,
967.1485595703125
],
"size": [
400,
200
],
"flags": {},
"order": 21,
"mode": 2,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 53
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
55
],
"slot_index": 0
}
],
"properties": {
"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"
]
},
{
"id": 48,
"type": "CLIPLoader",
"pos": [
394.15313720703125,
717.1484985351562
],
"size": [
315,
98.00003051757812
],
"flags": {},
"order": 0,
"mode": 2,
"inputs": [],
"outputs": [
{
"name": "CLIP",
"type": "CLIP",
"links": [
52,
53
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPLoader"
},
"widgets_values": [
"umt5_xxl_fp16.safetensors",
"wan",
"default"
]
},
{
"id": 49,
"type": "CLIPTextEncode",
"pos": [
754.153076171875,
717.1484985351562
],
"size": [
400,
200
],
"flags": {},
"order": 20,
"mode": 2,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 52
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
54
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"high quality nature video featuring a red panda balancing on a bamboo stem while a bird lands on it's head, on the background there is a waterfall"
]
},
{
"id": 27,
"type": "WanVideoSampler",
"pos": [
1315.2401123046875,
-401.48028564453125
],
"size": [
315,
699
],
"flags": {},
"order": 26,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "WANVIDEOMODEL",
"link": 29
},
{
"name": "text_embeds",
"type": "WANVIDEOTEXTEMBEDS",
"link": 30
},
{
"name": "image_embeds",
"type": "WANVIDIMAGE_EMBEDS",
"link": 64
},
{
"name": "samples",
"type": "LATENT",
"shape": 7,
"link": null
},
{
"name": "feta_args",
"type": "FETAARGS",
"shape": 7,
"link": 57
},
{
"name": "context_options",
"type": "WANVIDCONTEXT",
"shape": 7,
"link": null
},
{
"name": "teacache_args",
"type": "TEACACHEARGS",
"shape": 7,
"link": 56
},
{
"name": "flowedit_args",
"type": "FLOWEDITARGS",
"shape": 7,
"link": null
}
],
"outputs": [
{
"name": "samples",
"type": "LATENT",
"links": [
33
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "WanVideoSampler"
},
"widgets_values": [
25,
6,
5,
1057359483639287,
"fixed",
true,
"unipc",
0,
1,
""
]
},
{
"id": 42,
"type": "Note",
"pos": [
-580,
-760
],
"size": [
314.96246337890625,
152.77333068847656
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"Adjust the blocks to swap based on your VRAM, this is a tradeoff between speed and memory usage.\n\nAlternatively there's option to use VRAM management introduced in DiffSynt-Studios. This is usually slower, but saves even more VRAM compared to BlockSwap"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 45,
"type": "WanVideoVRAMManagement",
"pos": [
-210,
-580
],
"size": [
315,
58
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "vram_management_args",
"type": "VRAM_MANAGEMENTARGS",
"links": []
}
],
"properties": {
"Node name for S&R": "WanVideoVRAMManagement"
},
"widgets_values": [
1
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 36,
"type": "Note",
"pos": [
160,
-1010
],
"size": [
374.3061828613281,
171.9547576904297
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"fp8_fast seems to cause huge quality degradation\n\nfp_16_fast enables \"Full FP16 Accmumulation in FP16 GEMMs\" feature available in the very latest pytorch nightly, this is around 20% speed boost. \n\nSageattn if you have it installed can be used for almost double inference speed"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 33,
"type": "Note",
"pos": [
170,
-1150
],
"size": [
359.0753479003906,
88
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"Models:\nhttps://huggingface.co/Kijai/WanVideo_comfy/tree/main"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 51,
"type": "Note",
"pos": [
424.153076171875,
547.1480712890625
],
"size": [
253.16725158691406,
88
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"You can also use native ComfyUI text encoding with these nodes instead of the original, the models are node specific and can't otherwise be mixed."
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 60,
"type": "Note",
"pos": [
-432.5627136230469,
-224.5513458251953
],
"size": [
253.16725158691406,
88
],
"flags": {},
"order": 6,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"You can use either the original clip vision or the normal comfyui clip vision loader, they are the same model in the end."
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 62,
"type": "Note",
"pos": [
315.68389892578125,
215.8892364501953
],
"size": [
268.73455810546875,
90.03050994873047
],
"flags": {},
"order": 7,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"The original code had automatic resolution adjustment based on input image total pixels and aspect ratio. If you want to set it manually, disable the adjust_resolution"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 59,
"type": "CLIPVisionLoader",
"pos": [
-158.17127990722656,
-210.2847442626953
],
"size": [
315,
58
],
"flags": {},
"order": 8,
"mode": 2,
"inputs": [],
"outputs": [
{
"name": "CLIP_VISION",
"type": "CLIP_VISION",
"links": null
}
],
"properties": {
"Node name for S&R": "CLIPVisionLoader"
},
"widgets_values": [
"clip_vision_h.safetensors"
],
"color": "#2a363b",
"bgcolor": "#3f5159"
},
{
"id": 56,
"type": "LoadWanVideoClipTextEncoder",
"pos": [
-357.8293762207031,
-83.7756118774414
],
"size": [
510.6601257324219,
106
],
"flags": {},
"order": 9,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "wan_clip_vision",
"type": "CLIP_VISION",
"links": [
58
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "LoadWanVideoClipTextEncoder"
},
"widgets_values": [
"open-clip-xlm-roberta-large-vit-huge-14_visual_fp16.safetensors",
"fp16",
"offload_device"
],
"color": "#2a363b",
"bgcolor": "#3f5159"
},
{
"id": 57,
"type": "WanVideoImageClipEncode",
"pos": [
286.400390625,
-86.68402099609375
],
"size": [
315,
266
],
"flags": {},
"order": 23,
"mode": 0,
"inputs": [
{
"name": "clip_vision",
"type": "CLIP_VISION",
"link": 58
},
{
"name": "image",
"type": "IMAGE",
"link": 59
},
{
"name": "vae",
"type": "WANVAE",
"link": 63
}
],
"outputs": [
{
"name": "image_embeds",
"type": "WANVIDIMAGE_EMBEDS",
"links": [
64
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "WanVideoImageClipEncode"
},
"widgets_values": [
832,
480,
81,
true,
0.030000000000000006,
1,
1,
true
],
"color": "#2a363b",
"bgcolor": "#3f5159"
},
{
"id": 11,
"type": "LoadWanVideoT5TextEncoder",
"pos": [
161.7229461669922,
-501.2225036621094
],
"size": [
377.1661376953125,
130
],
"flags": {},
"order": 10,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "wan_t5_model",
"type": "WANTEXTENCODER",
"links": [
15
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "LoadWanVideoT5TextEncoder"
},
"widgets_values": [
"umt5-xxl-enc-bf16.safetensors",
"bf16",
"offload_device",
"disabled"
],
"color": "#332922",
"bgcolor": "#593930"
},
{
"id": 16,
"type": "WanVideoTextEncode",
"pos": [
787.8640747070312,
-91.52558898925781
],
"size": [
420.30511474609375,
261.5306701660156
],
"flags": {},
"order": 22,
"mode": 0,
"inputs": [
{
"name": "t5",
"type": "WANTEXTENCODER",
"link": 15
}
],
"outputs": [
{
"name": "text_embeds",
"type": "WANVIDEOTEXTEMBEDS",
"links": [
30
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "WanVideoTextEncode"
},
"widgets_values": [
"an old man is stroking his beard thoughtfully",
"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",
true
],
"color": "#332922",
"bgcolor": "#593930"
},
{
"id": 58,
"type": "LoadImage",
"pos": [
-275.1466369628906,
108.30052185058594
],
"size": [
413.10479736328125,
498.3180847167969
],
"flags": {},
"order": 11,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
59
]
},
{
"name": "MASK",
"type": "MASK",
"links": null
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"oldman_upscaled.png",
"image"
],
"color": "#2a363b",
"bgcolor": "#3f5159"
},
{
"id": 22,
"type": "WanVideoModelLoader",
"pos": [
150,
-780
],
"size": [
477.4410095214844,
226.43276977539062
],
"flags": {},
"order": 24,
"mode": 0,
"inputs": [
{
"name": "compile_args",
"type": "WANCOMPILEARGS",
"shape": 7,
"link": null
},
{
"name": "block_swap_args",
"type": "BLOCKSWAPARGS",
"shape": 7,
"link": 50
},
{
"name": "lora",
"type": "WANVIDLORA",
"shape": 7,
"link": null
},
{
"name": "vram_management_args",
"type": "VRAM_MANAGEMENTARGS",
"shape": 7,
"link": null
}
],
"outputs": [
{
"name": "model",
"type": "WANVIDEOMODEL",
"links": [
29
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "WanVideoModelLoader"
},
"widgets_values": [
"WanVideo\\Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors",
"fp16",
"fp8_e4m3fn",
"offload_device",
"sdpa"
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 55,
"type": "WanVideoEnhanceAVideo",
"pos": [
1312.6407470703125,
-596.7884521484375
],
"size": [
315,
106
],
"flags": {},
"order": 12,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "feta_args",
"type": "FETAARGS",
"links": [
57
]
}
],
"properties": {
"Node name for S&R": "WanVideoEnhanceAVideo"
},
"widgets_values": [
2,
0,
1
]
},
{
"id": 52,
"type": "WanVideoTeaCache",
"pos": [
1307.6705322265625,
-787.4303588867188
],
"size": [
315,
130
],
"flags": {},
"order": 13,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "teacache_args",
"type": "TEACACHEARGS",
"links": [
56
]
}
],
"properties": {
"Node name for S&R": "WanVideoTeaCache"
},
"widgets_values": [
0.030000000000000006,
6,
-1,
"offload_device"
]
},
{
"id": 54,
"type": "Note",
"pos": [
961.6879272460938,
-580.803466796875
],
"size": [
327.61932373046875,
88
],
"flags": {},
"order": 14,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"Enhance-a-video can increase the fidelity of the results, too high values lead to noisy results."
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 53,
"type": "Note",
"pos": [
960.3718872070312,
-810.77099609375
],
"size": [
324.64129638671875,
159.47401428222656
],
"flags": {},
"order": 15,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"TeaCache could be considered to be sort of an automated step skipper, it will compare the current and previous model inputs/outputs and their relative distances to determine if the step can be skipped-\n\nThe relative l1 threshold -value determines how aggressive this is, higher values are faster but quality suffers more. Start step should be around 10-20% into the process, very first steps should NEVER be skipped with this model or it kills the motion."
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 28,
"type": "WanVideoDecode",
"pos": [
1688.0194091796875,
-647.6461791992188
],
"size": [
315,
174
],
"flags": {},
"order": 27,
"mode": 0,
"inputs": [
{
"name": "vae",
"type": "WANVAE",
"link": 43
},
{
"name": "samples",
"type": "LATENT",
"link": 33
}
],
"outputs": [
{
"name": "images",
"type": "IMAGE",
"links": [
36
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "WanVideoDecode"
},
"widgets_values": [
true,
272,
272,
144,
128
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 35,
"type": "WanVideoTorchCompileSettings",
"pos": [
-276.8500671386719,
-1050.6326904296875
],
"size": [
390.5999755859375,
178
],
"flags": {},
"order": 16,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "torch_compile_args",
"type": "WANCOMPILEARGS",
"links": [],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "WanVideoTorchCompileSettings"
},
"widgets_values": [
"inductor",
false,
"default",
false,
64,
true
],
"color": "#223",
"bgcolor": "#335"
},
{
"id": 44,
"type": "Note",
"pos": [
-620.9041137695312,
-1049.732421875
],
"size": [
303.0501403808594,
88
],
"flags": {},
"order": 17,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {},
"widgets_values": [
"If you have Triton installed, connect this for ~30% speed increase"
],
"color": "#432",
"bgcolor": "#653"
},
{
"id": 30,
"type": "VHS_VideoCombine",
"pos": [
1684.1597900390625,
-394.2595520019531
],
"size": [
1245.8460693359375,
1573.8460693359375
],
"flags": {},
"order": 28,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 36
},
{
"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": 16,
"loop_count": 0,
"filename_prefix": "WanVideoWrapper_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": "WanVideo2_1_T2V_00256.mp4",
"subfolder": "",
"type": "output",
"format": "video/h264-mp4",
"frame_rate": 16,
"workflow": "WanVideo2_1_T2V_00256.png",
"fullpath": "N:\\AI\\ComfyUI\\output\\WanVideo2_1_T2V_00256.mp4"
}
}
}
},
{
"id": 38,
"type": "WanVideoVAELoader",
"pos": [
169.25408935546875,
-322.9471740722656
],
"size": [
372.7727966308594,
82
],
"flags": {},
"order": 18,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "vae",
"type": "WANVAE",
"links": [
43,
63
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "WanVideoVAELoader"
},
"widgets_values": [
"wanvideo\\Wan2_1_VAE_bf16.safetensors",
"bf16"
],
"color": "#322",
"bgcolor": "#533"
},
{
"id": 39,
"type": "WanVideoBlockSwap",
"pos": [
-210,
-760
],
"size": [
315,
106
],
"flags": {},
"order": 19,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "block_swap_args",
"type": "BLOCKSWAPARGS",
"links": [
50
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "WanVideoBlockSwap"
},
"widgets_values": [
20,
false,
false
],
"color": "#223",
"bgcolor": "#335"
}
],
"links": [
[
15,
11,
0,
16,
0,
"WANTEXTENCODER"
],
[
29,
22,
0,
27,
0,
"WANVIDEOMODEL"
],
[
30,
16,
0,
27,
1,
"WANVIDEOTEXTEMBEDS"
],
[
33,
27,
0,
28,
1,
"LATENT"
],
[
36,
28,
0,
30,
0,
"IMAGE"
],
[
43,
38,
0,
28,
0,
"VAE"
],
[
50,
39,
0,
22,
1,
"BLOCKSWAPARGS"
],
[
52,
48,
0,
49,
0,
"CLIP"
],
[
53,
48,
0,
50,
0,
"CLIP"
],
[
54,
49,
0,
46,
0,
"CONDITIONING"
],
[
55,
50,
0,
46,
1,
"CONDITIONING"
],
[
56,
52,
0,
27,
6,
"TEACACHEARGS"
],
[
57,
55,
0,
27,
4,
"FETAARGS"
],
[
58,
56,
0,
57,
0,
"CLIP_VISION"
],
[
59,
58,
0,
57,
1,
"IMAGE"
],
[
63,
38,
0,
57,
2,
"WANVAE"
],
[
64,
57,
0,
27,
2,
"WANVIDIMAGE_EMBEDS"
]
],
"groups": [
{
"id": 1,
"title": "ComfyUI text encoding alternative",
"bounding": [
331.337158203125,
403.2147216796875,
1210.621337890625,
805.9080810546875
],
"color": "#3f789e",
"font_size": 24,
"flags": {}
}
],
"config": {},
"extra": {
"ds": {
"scale": 0.4594972986357498,
"offset": [
1140.269833168491,
1117.2515633785054
]
},
"node_versions": {
"ComfyUI-WanVideoWrapper": "721cd65e7b5224c70a3d20446d9d561f1732216b",
"comfy-core": "0.3.19",
"ComfyUI-VideoHelperSuite": "2c25b8b53835aaeb63f831b3137c705cf9f85dce"
},
"VHS_latentpreview": true,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"version": 0.4
}