Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+result/output1.mp4 filter=lfs diff=lfs merge=lfs -text
+result/output2.mp4 filter=lfs diff=lfs merge=lfs -text
+result/output3.mp4 filter=lfs diff=lfs merge=lfs -text
+result/output4.mp4 filter=lfs diff=lfs merge=lfs -text
+result/output5.mp4 filter=lfs diff=lfs merge=lfs -text
+result/output6.mp4 filter=lfs diff=lfs merge=lfs -text
+result/test.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,136 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- Wan-AI/Wan2.1-I2V-14B-720P
+- Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
+pipeline_tag: image-to-video
+tags:
+- text-to-image
+- lora
+- diffusers
+- template:diffusion-lora
+widget:
+- text: >-
+    gangtiexia，背景保持不变，这个人开始变身白色机甲，变身过程中出现机甲面罩遮住脸部，变身完成之后这个人向前走
+  output:
+    url: result/output1.mp4
+- text: >-
+    gangtiexia，背景保持不变，这个人开始变身粉色机甲，变身过程中出现机甲面罩遮住脸部，变身完成之后这个人向前走
+  output:
+    url: result/output2.mp4
+- text: >-
+    gangtiexia，背景保持不变，这个人开始变身金色机甲，变身过程中出现机甲面罩遮住脸部，变身完成之后这个人向前走
+  output:
+    url: result/output3.mp4
+- text: >-
+    gangtiexia，背景保持不变，这个人开始变身金色机甲，变身过程中出现机甲面罩遮住脸部，变身完成之后这个人向前走
+  output:
+    url: result/output4.mp4
+- text: >-
+    gangtiexia，背景保持不变，这个人开始变身白色机甲，变身过程中出现机甲面罩遮住脸部，变身完成之后这个人向前走
+  output:
+    url: result/output5.mp4
+- text: >-
+    gangtiexia，背景保持不变，这个人开始变身红色机甲，变身过程中出现机甲面罩遮住脸部，变身完成之后这个人向前走
+  output:
+    url: result/output6.mp4
+
+---
+<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
+  <h1 style="color: #24292e; margin-top: 0;">valiantcat LoRA for Wan2.1 14B I2V 720p</h1>
+  
+  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
+    <h2 style="color: #24292e; margin-top: 0;">Overview</h2>
+    <p>This LoRA is trained on the Wan2.1 14B I2V 720p model.</p>
+  </div>
+
+  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
+    <h2 style="color: #24292e; margin-top: 0;">Features</h2>
+    <ul style="margin-bottom: 0;">
+      <li>Transform any image into a video of two people began to fight</li>
+      <li>Trained on the Wan2.1 14B 720p I2V base model</li>
+      <li>Consistent results across different object types</li>
+      <li>Simple prompt structure that's easy to adapt</li>
+    </ul>
+  </div>
+
+<Gallery />
+
+# Model File and Inference Workflow
+
+## 📥 Download Links:
+
+- [wan2.1-Mecha.safetensors](./wan2.1-Mecha.safetensors) - LoRA Model File
+- [wan_img2video_lora_workflow.json](./result/wan2.1-exmple.json) - Wan I2V with LoRA Workflow for ComfyUI
+
+## Using with Diffusers
+```py
+pip install git+https://github.com/huggingface/diffusers.git
+```
+
+```py
+import torch
+from diffusers.utils import export_to_video, load_image
+from diffusers import AutoencoderKLWan, WanImageToVideoPipeline
+from transformers import CLIPVisionModel
+import numpy as np
+
+model_id = "Wan-AI/Wan2.1-I2V-14B-720P-Diffusers"
+image_encoder = CLIPVisionModel.from_pretrained(model_id, subfolder="image_encoder", torch_dtype=torch.float32)
+vae = AutoencoderKLWan.from_pretrained(model_id, subfolder="vae", torch_dtype=torch.float32)
+pipe = WanImageToVideoPipeline.from_pretrained(model_id, vae=vae, image_encoder=image_encoder, torch_dtype=torch.bfloat16)
+pipe.to("cuda")
+
+pipe.load_lora_weights("valiantcat/Wan2.1-Mecha-LoRA")
+
+pipe.enable_model_cpu_offload() #for low-vram environments
+
+prompt = "gangtiexia，背景保持不变，这个人开始变身红色机甲，变身过程中出现机甲面罩遮住脸部，变身完成之后这个人向前走."
+
+image = load_image("https://huggingface.co/valiantcat/Wan2.1-Mecha-LoRA/blob/main/result/test.jpg")
+
+max_area = 512 * 768
+aspect_ratio = image.height / image.width
+mod_value = pipe.vae_scale_factor_spatial * pipe.transformer.config.patch_size[1]
+height = round(np.sqrt(max_area * aspect_ratio)) // mod_value * mod_value
+width = round(np.sqrt(max_area / aspect_ratio)) // mod_value * mod_value
+image = image.resize((width, height))
+
+output = pipe(
+    image=image,
+    prompt=prompt,
+    height=height,
+    width=width,
+    num_frames=81,
+    guidance_scale=5.0,
+    num_inference_steps=25
+).frames[0]
+export_to_video(output, "output.mp4", fps=16)
+```
+
+---
+<div style="background-color: #f8f9fa; padding: 20px; border-radius: 10px; margin-bottom: 20px;">
+  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
+    <h2 style="color: #24292e; margin-top: 0;">Recommended Settings</h2>
+    <ul style="margin-bottom: 0;">
+      <li><b>LoRA Strength:</b> 1.0</li>
+      <li><b>Embedded Guidance Scale:</b> 6.0</li>
+      <li><b>Flow Shift:</b> 5.0</li>
+    </ul>
+  </div>
+
+  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
+    <h2 style="color: #24292e; margin-top: 0;">Trigger Words</h2>
+    <p>The key trigger phrase is: <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;">gangtiexia</code></p>
+  </div>
+
+  <div style="background-color: white; padding: 15px; border-radius: 8px; margin: 15px 0; box-shadow: 0 2px 4px rgba(0,0,0,0.1);">
+    <h2 style="color: #24292e; margin-top: 0;">Prompt Template</h2>
+    <p>For best results, use this prompt structure:</p>
+    <div style="background-color: #f0f0f0; padding: 12px; border-radius: 6px; margin: 10px 0;">
+      <i>gangtiexia，背景保持不变，这个人开始变身[color]色机甲，变身过程中出现机甲面罩遮住脸部，变身完成之后这个人向前走</i>
+    </div>
+    <p>Simply replace <code style="background-color: #f0f0f0; padding: 3px 6px; border-radius: 4px;">[color]</code> with whatever you want to let this person transform into the color of a mecha</p>
+  </div>

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "ffn.2",
+    "ffn.0",
+    "k",
+    "v_img",
+    "k_img",
+    "o",
+    "v",
+    "q"
+  ],
+  "task_type": null,
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

result/output1.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39fda4fe7511a55ba97eb6d4ed0efcb0ced3ff57b2340d95c2a45f8ea390617e
+size 4313201

result/output2.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f61df2e027db6c7c3fe86338aef586f03b34d0490711b72fdcca899de89a99f0
+size 4549934

result/output3.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b057ee0caf3ee8d4eac48d04fef21a30c617d10de7199b8c3ebe4553ca4c7db6
+size 4614884

result/output4.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac80d71e55cdf381f811b4268d70c5196856fbc2015ba1d159759a33155e1031
+size 4872143

result/output5.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d1ba89af7647dbf2c7a8b2c7ad0f997040545eaa68c0aa30f2085cbb56190e4
+size 3144397

result/output6.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637445ed56aa8121b507bc19a87d306f7d4f14ed20d2907279a59858de595c4b
+size 4533217

result/wan2.1-exmple.json

@@ -0,0 +1,1406 @@
+{
+  "id": "d917b823-2929-4a83-b9a5-83af1dba5803",
+  "revision": 0,
+  "last_node_id": 59,
+  "last_link_id": 68,
+  "nodes": [
+    {
+      "id": 35,
+      "type": "WanVideoTorchCompileSettings",
+      "pos": [
+        1235.3983154296875,
+        -322.3111267089844
+      ],
+      "size": [
+        421.6000061035156,
+        202
+      ],
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "torch_compile_args",
+          "name": "torch_compile_args",
+          "type": "WANCOMPILEARGS",
+          "slot_index": 0,
+          "links": []
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "ef65c86b1daf49c30d7c51e0a9173c1a3056d6a9",
+        "Node name for S&R": "WanVideoTorchCompileSettings"
+      },
+      "widgets_values": [
+        "inductor",
+        false,
+        "default",
+        false,
+        64,
+        true,
+        128
+      ]
+    },
+    {
+      "id": 13,
+      "type": "LoadWanVideoClipTextEncoder",
+      "pos": [
+        -37.884437561035156,
+        152.7856903076172
+      ],
+      "size": [
+        384.08111572265625,
+        111.7017593383789
+      ],
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "wan_clip_vision",
+          "name": "wan_clip_vision",
+          "type": "CLIP_VISION",
+          "slot_index": 0,
+          "links": [
+            17
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "ef65c86b1daf49c30d7c51e0a9173c1a3056d6a9",
+        "Node name for S&R": "LoadWanVideoClipTextEncoder"
+      },
+      "widgets_values": [
+        "open-clip-xlm-roberta-large-vit-huge-14_visual_fp32.safetensors",
+        "fp16",
+        "offload_device"
+      ]
+    },
+    {
+      "id": 21,
+      "type": "WanVideoVAELoader",
+      "pos": [
+        -37.18030548095703,
+        312.3882141113281
+      ],
+      "size": [
+        381.5052795410156,
+        91.97122192382812
+      ],
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "vae",
+          "name": "vae",
+          "type": "WANVAE",
+          "slot_index": 0,
+          "links": [
+            21,
+            34
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "ef65c86b1daf49c30d7c51e0a9173c1a3056d6a9",
+        "Node name for S&R": "WanVideoVAELoader"
+      },
+      "widgets_values": [
+        "Wan2_1_VAE_bf16.safetensors",
+        "fp16"
+      ]
+    },
+    {
+      "id": 32,
+      "type": "WanVideoBlockSwap",
+      "pos": [
+        -6.692852020263672,
+        -173.05665588378906
+      ],
+      "size": [
+        315,
+        154
+      ],
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "block_swap_args",
+          "name": "block_swap_args",
+          "type": "BLOCKSWAPARGS",
+          "slot_index": 0,
+          "links": [
+            39
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "ef65c86b1daf49c30d7c51e0a9173c1a3056d6a9",
+        "Node name for S&R": "WanVideoBlockSwap"
+      },
+      "widgets_values": [
+        10,
+        false,
+        false,
+        true,
+        0
+      ]
+    },
+    {
+      "id": 22,
+      "type": "WanVideoModelLoader",
+      "pos": [
+        342.6396484375,
+        -329.9376525878906
+      ],
+      "size": [
+        477.4410095214844,
+        274
+      ],
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "label": "compile_args",
+          "name": "compile_args",
+          "shape": 7,
+          "type": "WANCOMPILEARGS",
+          "link": null
+        },
+        {
+          "label": "block_swap_args",
+          "name": "block_swap_args",
+          "shape": 7,
+          "type": "BLOCKSWAPARGS",
+          "link": 39
+        },
+        {
+          "label": "lora",
+          "name": "lora",
+          "shape": 7,
+          "type": "WANVIDLORA",
+          "link": null
+        },
+        {
+          "label": "vram_management_args",
+          "name": "vram_management_args",
+          "shape": 7,
+          "type": "VRAM_MANAGEMENTARGS",
+          "link": null
+        },
+        {
+          "label": "vace_model",
+          "name": "vace_model",
+          "shape": 7,
+          "type": "VACEPATH",
+          "link": null
+        },
+        {
+          "label": "fantasytalking_model",
+          "name": "fantasytalking_model",
+          "shape": 7,
+          "type": "FANTASYTALKINGMODEL",
+          "link": null
+        },
+        {
+          "label": "multitalk_model",
+          "name": "multitalk_model",
+          "shape": 7,
+          "type": "MULTITALKMODEL",
+          "link": null
+        }
+      ],
+      "outputs": [
+        {
+          "label": "model",
+          "name": "model",
+          "type": "WANVIDEOMODEL",
+          "slot_index": 0,
+          "links": [
+            29
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "ef65c86b1daf49c30d7c51e0a9173c1a3056d6a9",
+        "Node name for S&R": "WanVideoModelLoader"
+      },
+      "widgets_values": [
+        "Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors",
+        "bf16",
+        "fp8_e4m3fn",
+        "offload_device",
+        "sageattn"
+      ]
+    },
+    {
+      "id": 52,
+      "type": "String",
+      "pos": [
+        302.2411193847656,
+        844.2974853515625
+      ],
+      "size": [
+        400,
+        200
+      ],
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "字符串",
+          "name": "STRING",
+          "type": "STRING",
+          "slot_index": 0,
+          "links": [
+            55
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfyliterals",
+        "ver": "bdddb08ca82d90d75d97b1d437a652e0284a32ac",
+        "Node name for S&R": "String"
+      },
+      "widgets_values": [
+        "Colorful, overexposed, static, blurred details, subtitles, style, work, painting, picture, still, overall gray, worst quality, low quality, JPEG compression residue, ugly, mutilated, redundant fingers, poorly painted hands, poorly painted faces, deformed, disfigured, deformed limbs, fused fingers, still pictures, Messy background, three legs, a lot of people in the background, go backwards",
+        [
+          false,
+          true
+        ]
+      ]
+    },
+    {
+      "id": 11,
+      "type": "LoadWanVideoT5TextEncoder",
+      "pos": [
+        -39.758052825927734,
+        -23.7592716217041
+      ],
+      "size": [
+        377.1661376953125,
+        130
+      ],
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "wan_t5_model",
+          "name": "wan_t5_model",
+          "type": "WANTEXTENCODER",
+          "slot_index": 0,
+          "links": [
+            58
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "ef65c86b1daf49c30d7c51e0a9173c1a3056d6a9",
+        "Node name for S&R": "LoadWanVideoT5TextEncoder"
+      },
+      "widgets_values": [
+        "umt5-xxl-enc-bf16.safetensors",
+        "bf16",
+        "offload_device",
+        "disabled"
+      ]
+    },
+    {
+      "id": 57,
+      "type": "WanVideoExperimentalArgs",
+      "pos": [
+        858.3304443359375,
+        266.7475280761719
+      ],
+      "size": [
+        327.5999755859375,
+        226
+      ],
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "exp_args",
+          "name": "exp_args",
+          "type": "EXPERIMENTALARGS",
+          "links": [
+            59
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "9100eecccf8437e3a0e4be5fc7004c809db18ee6",
+        "Node name for S&R": "WanVideoExperimentalArgs"
+      },
+      "widgets_values": [
+        "",
+        false,
+        true,
+        0,
+        false,
+        1,
+        1.25,
+        20
+      ]
+    },
+    {
+      "id": 55,
+      "type": "WanVideoSLG",
+      "pos": [
+        848.3304443359375,
+        96.74756622314453
+      ],
+      "size": [
+        340.34442138671875,
+        112.611572265625
+      ],
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "slg_args",
+          "name": "slg_args",
+          "type": "SLGARGS",
+          "links": [
+            60
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "9100eecccf8437e3a0e4be5fc7004c809db18ee6",
+        "Node name for S&R": "WanVideoSLG"
+      },
+      "widgets_values": [
+        "9",
+        0,
+        0.8000000000000002
+      ]
+    },
+    {
+      "id": 54,
+      "type": "WanVideoTeaCache",
+      "pos": [
+        868.3304443359375,
+        -333.25244140625
+      ],
+      "size": [
+        315,
+        178
+      ],
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "cache_args",
+          "name": "cache_args",
+          "type": "CACHEARGS",
+          "links": [
+            62
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "9100eecccf8437e3a0e4be5fc7004c809db18ee6",
+        "Node name for S&R": "WanVideoTeaCache"
+      },
+      "widgets_values": [
+        0.2,
+        6,
+        -1,
+        "offload_device",
+        true,
+        "e"
+      ]
+    },
+    {
+      "id": 17,
+      "type": "WanVideoImageClipEncode",
+      "pos": [
+        467.3199157714844,
+        20.125715255737305
+      ],
+      "size": [
+        319.20001220703125,
+        306
+      ],
+      "flags": {},
+      "order": 16,
+      "mode": 0,
+      "inputs": [
+        {
+          "label": "clip_vision",
+          "name": "clip_vision",
+          "type": "CLIP_VISION",
+          "link": 17
+        },
+        {
+          "label": "image",
+          "name": "image",
+          "type": "IMAGE",
+          "link": 66
+        },
+        {
+          "label": "vae",
+          "name": "vae",
+          "type": "WANVAE",
+          "link": 21
+        },
+        {
+          "label": "generation_width",
+          "name": "generation_width",
+          "type": "INT",
+          "widget": {
+            "name": "generation_width"
+          },
+          "link": 67
+        },
+        {
+          "label": "generation_height",
+          "name": "generation_height",
+          "type": "INT",
+          "widget": {
+            "name": "generation_height"
+          },
+          "link": 68
+        }
+      ],
+      "outputs": [
+        {
+          "label": "image_embeds",
+          "name": "image_embeds",
+          "type": "WANVIDIMAGE_EMBEDS",
+          "slot_index": 0,
+          "links": [
+            32
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "ef65c86b1daf49c30d7c51e0a9173c1a3056d6a9",
+        "Node name for S&R": "WanVideoImageClipEncode"
+      },
+      "widgets_values": [
+        440,
+        440,
+        81,
+        true,
+        0,
+        1,
+        1,
+        true
+      ]
+    },
+    {
+      "id": 27,
+      "type": "WanVideoSampler",
+      "pos": [
+        1292.3868408203125,
+        -41.239501953125
+      ],
+      "size": [
+        315,
+        750
+      ],
+      "flags": {},
+      "order": 17,
+      "mode": 0,
+      "inputs": [
+        {
+          "label": "model",
+          "name": "model",
+          "type": "WANVIDEOMODEL",
+          "link": 29
+        },
+        {
+          "label": "image_embeds",
+          "name": "image_embeds",
+          "type": "WANVIDIMAGE_EMBEDS",
+          "link": 32
+        },
+        {
+          "label": "text_embeds",
+          "name": "text_embeds",
+          "shape": 7,
+          "type": "WANVIDEOTEXTEMBEDS",
+          "link": 57
+        },
+        {
+          "label": "samples",
+          "name": "samples",
+          "shape": 7,
+          "type": "LATENT",
+          "link": null
+        },
+        {
+          "label": "feta_args",
+          "name": "feta_args",
+          "shape": 7,
+          "type": "FETAARGS",
+          "link": 61
+        },
+        {
+          "label": "context_options",
+          "name": "context_options",
+          "shape": 7,
+          "type": "WANVIDCONTEXT",
+          "link": null
+        },
+        {
+          "label": "cache_args",
+          "name": "cache_args",
+          "shape": 7,
+          "type": "CACHEARGS",
+          "link": null
+        },
+        {
+          "label": "flowedit_args",
+          "name": "flowedit_args",
+          "shape": 7,
+          "type": "FLOWEDITARGS",
+          "link": null
+        },
+        {
+          "label": "slg_args",
+          "name": "slg_args",
+          "shape": 7,
+          "type": "SLGARGS",
+          "link": 60
+        },
+        {
+          "label": "loop_args",
+          "name": "loop_args",
+          "shape": 7,
+          "type": "LOOPARGS",
+          "link": null
+        },
+        {
+          "label": "experimental_args",
+          "name": "experimental_args",
+          "shape": 7,
+          "type": "EXPERIMENTALARGS",
+          "link": 59
+        },
+        {
+          "label": "sigmas",
+          "name": "sigmas",
+          "shape": 7,
+          "type": "SIGMAS",
+          "link": null
+        },
+        {
+          "label": "unianimate_poses",
+          "name": "unianimate_poses",
+          "shape": 7,
+          "type": "UNIANIMATE_POSE",
+          "link": null
+        },
+        {
+          "label": "fantasytalking_embeds",
+          "name": "fantasytalking_embeds",
+          "shape": 7,
+          "type": "FANTASYTALKING_EMBEDS",
+          "link": null
+        },
+        {
+          "label": "uni3c_embeds",
+          "name": "uni3c_embeds",
+          "shape": 7,
+          "type": "UNI3C_EMBEDS",
+          "link": null
+        },
+        {
+          "label": "multitalk_embeds",
+          "name": "multitalk_embeds",
+          "shape": 7,
+          "type": "MULTITALK_EMBEDS",
+          "link": null
+        },
+        {
+          "label": "freeinit_args",
+          "name": "freeinit_args",
+          "shape": 7,
+          "type": "FREEINITARGS",
+          "link": null
+        },
+        {
+          "label": "seed",
+          "name": "seed",
+          "type": "INT",
+          "widget": {
+            "name": "seed"
+          },
+          "link": 63
+        },
+        {
+          "label": "teacache_args",
+          "name": "teacache_args",
+          "shape": 7,
+          "type": "TEACACHEARGS",
+          "link": 62
+        }
+      ],
+      "outputs": [
+        {
+          "label": "samples",
+          "name": "samples",
+          "type": "LATENT",
+          "slot_index": 0,
+          "links": [
+            33
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "ef65c86b1daf49c30d7c51e0a9173c1a3056d6a9",
+        "Node name for S&R": "WanVideoSampler"
+      },
+      "widgets_values": [
+        20,
+        6,
+        5,
+        675416533409962,
+        "randomize",
+        true,
+        "dpm++",
+        0,
+        1,
+        false,
+        "comfy"
+      ]
+    },
+    {
+      "id": 56,
+      "type": "WanVideoEnhanceAVideo",
+      "pos": [
+        866.8117065429688,
+        -90.16363525390625
+      ],
+      "size": [
+        315,
+        106
+      ],
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "feta_args",
+          "name": "feta_args",
+          "type": "FETAARGS",
+          "links": [
+            61
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "9100eecccf8437e3a0e4be5fc7004c809db18ee6",
+        "Node name for S&R": "WanVideoEnhanceAVideo"
+      },
+      "widgets_values": [
+        2,
+        0,
+        1
+      ]
+    },
+    {
+      "id": 53,
+      "type": "WanVideoTextEncode",
+      "pos": [
+        806.1103515625,
+        582.8258056640625
+      ],
+      "size": [
+        400,
+        206
+      ],
+      "flags": {},
+      "order": 15,
+      "mode": 0,
+      "inputs": [
+        {
+          "label": "t5",
+          "name": "t5",
+          "type": "WANTEXTENCODER",
+          "link": 58
+        },
+        {
+          "label": "model_to_offload",
+          "name": "model_to_offload",
+          "shape": 7,
+          "type": "WANVIDEOMODEL",
+          "link": null
+        },
+        {
+          "label": "positive_prompt",
+          "name": "positive_prompt",
+          "type": "STRING",
+          "widget": {
+            "name": "positive_prompt"
+          },
+          "link": 56
+        },
+        {
+          "label": "negative_prompt",
+          "name": "negative_prompt",
+          "type": "STRING",
+          "widget": {
+            "name": "negative_prompt"
+          },
+          "link": 55
+        }
+      ],
+      "outputs": [
+        {
+          "label": "text_embeds",
+          "name": "text_embeds",
+          "type": "WANVIDEOTEXTEMBEDS",
+          "links": [
+            57
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "e5a326c9811514f2c08c89bccea9a7c731d9a503",
+        "Node name for S&R": "WanVideoTextEncode"
+      },
+      "widgets_values": [
+        "",
+        "",
+        true,
+        [
+          false,
+          true
+        ],
+        [
+          false,
+          true
+        ]
+      ]
+    },
+    {
+      "id": 58,
+      "type": "Seed (rgthree)",
+      "pos": [
+        872.7892456054688,
+        846.89599609375
+      ],
+      "size": [
+        244.73599243164062,
+        130
+      ],
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "dir": 4,
+          "label": "随机种",
+          "name": "SEED",
+          "shape": 3,
+          "type": "INT",
+          "links": [
+            63
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "rgthree-comfy",
+        "ver": "f044a9dbb3fc9de55c6244d616d386986add3072"
+      },
+      "widgets_values": [
+        -1,
+        "",
+        "",
+        ""
+      ]
+    },
+    {
+      "id": 28,
+      "type": "WanVideoDecode",
+      "pos": [
+        1663.38427734375,
+        537.8952026367188
+      ],
+      "size": [
+        315,
+        198
+      ],
+      "flags": {},
+      "order": 18,
+      "mode": 0,
+      "inputs": [
+        {
+          "label": "vae",
+          "name": "vae",
+          "type": "WANVAE",
+          "link": 34
+        },
+        {
+          "label": "samples",
+          "name": "samples",
+          "type": "LATENT",
+          "link": 33
+        }
+      ],
+      "outputs": [
+        {
+          "label": "images",
+          "name": "images",
+          "type": "IMAGE",
+          "slot_index": 0,
+          "links": [
+            36
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "ComfyUI-WanVideoWrapper",
+        "ver": "ef65c86b1daf49c30d7c51e0a9173c1a3056d6a9",
+        "Node name for S&R": "WanVideoDecode"
+      },
+      "widgets_values": [
+        true,
+        272,
+        272,
+        144,
+        128,
+        "default"
+      ]
+    },
+    {
+      "id": 18,
+      "type": "LoadImage",
+      "pos": [
+        0.12228646874427795,
+        510.14959716796875
+      ],
+      "size": [
+        255.50192260742188,
+        314
+      ],
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "图像",
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "slot_index": 0,
+          "links": [
+            64
+          ]
+        },
+        {
+          "label": "遮罩",
+          "name": "MASK",
+          "type": "MASK",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfy-core",
+        "ver": "0.3.26",
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "test3.png",
+        "image"
+      ]
+    },
+    {
+      "id": 59,
+      "type": "LayerUtility: ImageScaleByAspectRatio V2",
+      "pos": [
+        -13.176090240478516,
+        869.6483764648438
+      ],
+      "size": [
+        270,
+        330
+      ],
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [
+        {
+          "label": "图像",
+          "name": "image",
+          "shape": 7,
+          "type": "IMAGE",
+          "link": 64
+        },
+        {
+          "label": "遮罩",
+          "name": "mask",
+          "shape": 7,
+          "type": "MASK",
+          "link": null
+        }
+      ],
+      "outputs": [
+        {
+          "label": "图像",
+          "name": "image",
+          "type": "IMAGE",
+          "links": [
+            66
+          ]
+        },
+        {
+          "label": "遮罩",
+          "name": "mask",
+          "type": "MASK",
+          "links": null
+        },
+        {
+          "label": "原始大小",
+          "name": "original_size",
+          "type": "BOX",
+          "links": null
+        },
+        {
+          "name": "width",
+          "type": "INT",
+          "links": [
+            67
+          ]
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": [
+            68
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfyui_layerstyle",
+        "ver": "c0fb64d0ebcb81c6c445a8af79ecee24bc3845b0",
+        "Node name for S&R": "LayerUtility: ImageScaleByAspectRatio V2"
+      },
+      "widgets_values": [
+        "original",
+        1,
+        1,
+        "letterbox",
+        "lanczos",
+        "16",
+        "longest",
+        768,
+        "#000000"
+      ],
+      "color": "rgba(38, 73, 116, 0.7)"
+    },
+    {
+      "id": 47,
+      "type": "String",
+      "pos": [
+        296.9170837402344,
+        543.8240966796875
+      ],
+      "size": [
+        400,
+        200
+      ],
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [],
+      "outputs": [
+        {
+          "label": "字符串",
+          "name": "STRING",
+          "type": "STRING",
+          "slot_index": 0,
+          "links": [
+            56
+          ]
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfyliterals",
+        "ver": "bdddb08ca82d90d75d97b1d437a652e0284a32ac",
+        "Node name for S&R": "String"
+      },
+      "widgets_values": [
+        "faxiang，背景保持不变，这个女人双手合十，身后出现巨大半透明粉色虚影法相，与女人动作同步",
+        [
+          false,
+          true
+        ]
+      ]
+    },
+    {
+      "id": 30,
+      "type": "VHS_VideoCombine",
+      "pos": [
+        1670.7396240234375,
+        -329.7770080566406
+      ],
+      "size": [
+        386.8522644042969,
+        334
+      ],
+      "flags": {},
+      "order": 19,
+      "mode": 0,
+      "inputs": [
+        {
+          "label": "图像",
+          "name": "images",
+          "type": "IMAGE",
+          "link": 36
+        },
+        {
+          "label": "音频",
+          "name": "audio",
+          "shape": 7,
+          "type": "AUDIO",
+          "link": null
+        },
+        {
+          "label": "批次管理",
+          "name": "meta_batch",
+          "shape": 7,
+          "type": "VHS_BatchManager",
+          "link": null
+        },
+        {
+          "name": "vae",
+          "shape": 7,
+          "type": "VAE",
+          "link": null
+        }
+      ],
+      "outputs": [
+        {
+          "label": "文件名",
+          "name": "Filenames",
+          "type": "VHS_FILENAMES",
+          "links": null
+        }
+      ],
+      "properties": {
+        "cnr_id": "comfyui-videohelpersuite",
+        "ver": "6953fa21443cf55f7c3b61ed3f4c87c5d3677fe1",
+        "Node name for S&R": "VHS_VideoCombine"
+      },
+      "widgets_values": {
+        "frame_rate": 16,
+        "loop_count": 0,
+        "filename_prefix": "Wan",
+        "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": "Wan_00191.mp4",
+            "subfolder": "",
+            "type": "output",
+            "format": "video/h264-mp4",
+            "frame_rate": 16,
+            "workflow": "Wan_00191.png",
+            "fullpath": "/root/tangfan/code/ComfyUI/output/Wan_00191.mp4"
+          }
+        }
+      }
+    }
+  ],
+  "links": [
+    [
+      17,
+      13,
+      0,
+      17,
+      0,
+      "WANCLIP"
+    ],
+    [
+      21,
+      21,
+      0,
+      17,
+      2,
+      "VAE"
+    ],
+    [
+      29,
+      22,
+      0,
+      27,
+      0,
+      "WANVIDEOMODEL"
+    ],
+    [
+      32,
+      17,
+      0,
+      27,
+      1,
+      "WANVIDIMAGE_EMBEDS"
+    ],
+    [
+      33,
+      27,
+      0,
+      28,
+      1,
+      "LATENT"
+    ],
+    [
+      34,
+      21,
+      0,
+      28,
+      0,
+      "VAE"
+    ],
+    [
+      36,
+      28,
+      0,
+      30,
+      0,
+      "IMAGE"
+    ],
+    [
+      39,
+      32,
+      0,
+      22,
+      1,
+      "BLOCKSWAPARGS"
+    ],
+    [
+      55,
+      52,
+      0,
+      53,
+      3,
+      "STRING"
+    ],
+    [
+      56,
+      47,
+      0,
+      53,
+      2,
+      "STRING"
+    ],
+    [
+      57,
+      53,
+      0,
+      27,
+      2,
+      "WANVIDEOTEXTEMBEDS"
+    ],
+    [
+      58,
+      11,
+      0,
+      53,
+      0,
+      "WANTEXTENCODER"
+    ],
+    [
+      59,
+      57,
+      0,
+      27,
+      10,
+      "EXPERIMENTALARGS"
+    ],
+    [
+      60,
+      55,
+      0,
+      27,
+      8,
+      "SLGARGS"
+    ],
+    [
+      61,
+      56,
+      0,
+      27,
+      4,
+      "FETAARGS"
+    ],
+    [
+      62,
+      54,
+      0,
+      27,
+      18,
+      "TEACACHEARGS"
+    ],
+    [
+      63,
+      58,
+      0,
+      27,
+      17,
+      "INT"
+    ],
+    [
+      64,
+      18,
+      0,
+      59,
+      0,
+      "IMAGE"
+    ],
+    [
+      66,
+      59,
+      0,
+      17,
+      1,
+      "IMAGE"
+    ],
+    [
+      67,
+      59,
+      3,
+      17,
+      3,
+      "INT"
+    ],
+    [
+      68,
+      59,
+      4,
+      17,
+      4,
+      "INT"
+    ]
+  ],
+  "groups": [
+    {
+      "id": 1,
+      "title": "输入端",
+      "bounding": [
+        -39.8446044921875,
+        434.6207275390625,
+        816.2230834960938,
+        714.2947998046875
+      ],
+      "color": "#3f789e",
+      "font_size": 24,
+      "flags": {}
+    },
+    {
+      "id": 2,
+      "title": "模型加载",
+      "bounding": [
+        -49.758056640625,
+        -403.53765869140625,
+        879.838623046875,
+        817.8970947265625
+      ],
+      "color": "#3f789e",
+      "font_size": 24,
+      "flags": {}
+    },
+    {
+      "id": 3,
+      "title": "Wan2.1-Latent",
+      "bounding": [
+        1225.3983154296875,
+        -405.9111328125,
+        816.852294921875,
+        1187.5999755859375
+      ],
+      "color": "#3f789e",
+      "font_size": 24,
+      "flags": {}
+    },
+    {
+      "id": 4,
+      "title": "配置参数",
+      "bounding": [
+        838.3304443359375,
+        -406.8524475097656,
+        365,
+        909.5999755859375
+      ],
+      "color": "#3f789e",
+      "font_size": 24,
+      "flags": {}
+    }
+  ],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.7972024500000007,
+      "offset": [
+        40.239255635647226,
+        575.6857199407289
+      ]
+    },
+    "frontendVersion": "1.23.4",
+    "node_versions": {
+      "ComfyUI-WanVideoWrapper": "4ce7e41492822e25f513f219ae11b1e0ff204b2a",
+      "ComfyUI-VideoHelperSuite": "565208bfe0a8050193ae3c8e61c96b6200dd9506",
+      "comfy-core": "0.3.18"
+    },
+    "VHS_latentpreview": false,
+    "VHS_latentpreviewrate": 0,
+    "VHS_MetadataImage": true,
+    "VHS_KeepIntermediate": true,
+    "ue_links": [],
+    "workspace_info": {
+      "id": "mZ-DLut47Mni3MFPHoL4Y",
+      "saveLock": false,
+      "cloudID": null,
+      "coverMediaPath": null
+    },
+    "0246.VERSION": [
+      0,
+      0,
+      4
+    ]
+  },
+  "version": 0.4
+}

wan2.1-Mecha.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7cf3c559567d2da5f5ac9f8f54c663f97c8a7a23bdb4e5061bfc4f72fd296d
+size 359257680