WAN 2.2 万相图生视频大模型

WAN 2.2 NF/SW 万相图生视频模型是一款基于 Wan Video 2.2 I2V-A14B 架构深度训练的专业级大模型，依托海量图像 - 视频配对数据与先进的时空建模技术，能够精准捕捉原图的细节特征与风格调性，高效生成流畅自然、风格统一的视频内容，适配多场景下的图生视频创作需求。

该模型用途广泛，但如有特定需求，请毫不犹豫地使用其他LoRa算法。同时，为了尽可能保留人脸特征，请适当降低LoRa算法的强度。

关于Fast Move V2版本

• 更好地理解
• 更好地理解相机
• 减少姿势之外不必要的前后移动
  （无法完全消除，但可大幅减少）
• 改善臀部弹跳效果
• 如果一名男子出现，他不会再自动试图在女子LT时与其发生关系。

这个版本是为那些想要更多动态场景和更多动作的用户设计的。

不同拍摄角度的示例提示

(at 0 seconds: wide frontal shot of a man standing in front of an open fridge, cinematic lighting, subtle ambient kitchen reflections, the fridge contents visible, camera static).
(at 1 second: medium shot from the front as he opens the fridge fully, reaches for a can, slight zoom-in to emphasize the action, cinematic framing).
(at 2 seconds: camera shifts to a side medium shot, tracking him as he lifts the can to his mouth, fluid movement, maintaining lighting and reflections).
(at 3 seconds: camera starts a smooth 360-degree orbit around the man, following him as he drinks from the can, motion fluid, background slightly blurred for cinematic effect).
(at 4 seconds: close-up on his face and upper body while drinking, orbit continues subtly, fridge reflections accentuating realism, cinematic polish).
(at 5 seconds: final wide shot as he lowers the can, camera completes orbit to original angle, showcasing the kitchen space, lighting, and dynamic movement).

可用的镜头运动

变焦/推拉

• zoom in
• zoom out
• camera zooms in on subject
• camera zooms out gradually
• dolly in
• dolly out
• camera dollies in slowly
• camera dollies out steadily
• crash zoom

平底锅

• pan left
• pan right
• camera pans across the scene
• gentle pan left
• sweeping pan right

倾斜

• tilt up
• tilt down
• camera tilts up to reveal…
• camera tilts down from…

轨道/跟踪/弧线/旋转

• orbit around subject
• 360° orbit
• camera circles around
• tracking shot
• camera tracks alongside subject
• arc shot
• curved camera movement

其他运动和风格

• static camera / static shot
• handheld shot
• camera roll

注意：
LoRA 与此模型完美兼容，在各种样式和概念中提供完全兼容性和一致的结果。

# 补充建议

不要犹豫使用否定提示。这在WAN视频中非常重要，它可以极大地改善您的视频质量，或者移除您不想看到的元素。一定要使用否定提示！

这里，模型应该将CFG 设置为 1，因此默认情况下负数信号不会工作，但有一个节点可以启用它们。使用方法很简单：打开管理器，输入kjnode，下载它，然后在你的工作流程中输入WAN Nag。这就是它的使用方法。将节点连接到你的 LoRA 加载器之后，使其与negative关联，最后将其放置在你的第一个 kSampler（high）中。

以下是针对不希望出现的移动的否定提示：
motion artifacts, animation artifacts, movement blur, motion distortion, dynamic distortion, shifting shapes, unstable render, instability, wobbling effect, jittering effect, vibrating render, inaccurate details, visual noise, distorted surfaces, rendering errors, warped shapes, exaggerated butt movement, jiggle, overanimated hips, unnatural butt motion, hyper bounce, extreme curves, distorted hips, unnatural pose, unrealistic anatomy, deformed body, disproportionate body, floating limbs, blurry textures, clipping, stretching, low detail, messy background, artifacts, butt bounce, moving hips, swinging hips, shaking butt, wiggling butt, moving lower body, moving pelvis, jiggling buttocks, bouncing butt, unstable stance, unnatural hip motion, exaggerated hip movement, hip sway, hip rotation, bottom motion, pelvis motion, wobbling hips, fidgeting lower body, dancing hips, pelvic movement, motion blur, unnatural movement

以下是来自 ComfyUI 官方工作流程的否定提示：
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

注意：如果您使用不带节点的默认工作流程，则此否定提示将不起作用。

作品参照

stand firmly with one leg, raise the other leg up and straight.

A young witch (Atsuko Kagari from Little Witch Academia) is sitting in a subway car. she is annoyed, looking away, holding a broom. 

She is crossing her legs and adjusting her dress (pushing down her dress near hthe hip). she then look at the viewer and give him a middle finger with her hand.

In the background through the subway windows is a city with a sunset. detailed background, dim light, low contrast, soft backlighting.
Negative prompt: motion artifacts, animation artifacts, movement blur, motion distortion, dynamic distortion, shifting shapes, unstable render, instability, wobbling effect, jittering effect, vibrating render, inaccurate details, visual noise, distorted surfaces, rendering errors, warped shapes,
Steps: 6, CFG scale: 1, Sampler: Euler a, Seed: 805290108177909

WAN 2.2 NF/SW 万相图生视频模型是一款基于 Wan Video 2.2 I2V-A14B 架构深度训练的专业级大模型，依托海量图像 - 视频配对数据与先进的时空建模技术，能够精准捕捉原图的细节特征与风格调性，高效生成流畅自然、风格统一的视频内容，适配多场景下的图生视频创作需求。

该模型用途广泛，但如有特定需求，请毫不犹豫地使用其他LoRa算法。同时，为了尽可能保留人脸特征，请适当降低LoRa算法的强度。

关于Fast Move V2版本

• 更好地理解
• 更好地理解相机
• 减少姿势之外不必要的前后移动
  （无法完全消除，但可大幅减少）
• 改善臀部弹跳效果
• 如果一名男子出现，他不会再自动试图在女子LT时与其发生关系。

这个版本是为那些想要更多动态场景和更多动作的用户设计的。

不同拍摄角度的示例提示

(at 0 seconds: wide frontal shot of a man standing in front of an open fridge, cinematic lighting, subtle ambient kitchen reflections, the fridge contents visible, camera static).
(at 1 second: medium shot from the front as he opens the fridge fully, reaches for a can, slight zoom-in to emphasize the action, cinematic framing).
(at 2 seconds: camera shifts to a side medium shot, tracking him as he lifts the can to his mouth, fluid movement, maintaining lighting and reflections).
(at 3 seconds: camera starts a smooth 360-degree orbit around the man, following him as he drinks from the can, motion fluid, background slightly blurred for cinematic effect).
(at 4 seconds: close-up on his face and upper body while drinking, orbit continues subtly, fridge reflections accentuating realism, cinematic polish).
(at 5 seconds: final wide shot as he lowers the can, camera completes orbit to original angle, showcasing the kitchen space, lighting, and dynamic movement).

可用的镜头运动

变焦/推拉

• zoom in
• zoom out
• camera zooms in on subject
• camera zooms out gradually
• dolly in
• dolly out
• camera dollies in slowly
• camera dollies out steadily
• crash zoom

平底锅

• pan left
• pan right
• camera pans across the scene
• gentle pan left
• sweeping pan right

倾斜

• tilt up
• tilt down
• camera tilts up to reveal…
• camera tilts down from…

轨道/跟踪/弧线/旋转

• orbit around subject
• 360° orbit
• camera circles around
• tracking shot
• camera tracks alongside subject
• arc shot
• curved camera movement

其他运动和风格

• static camera / static shot
• handheld shot
• camera roll

注意：
LoRA 与此模型完美兼容，在各种样式和概念中提供完全兼容性和一致的结果。

# 补充建议

不要犹豫使用否定提示。这在WAN视频中非常重要，它可以极大地改善您的视频质量，或者移除您不想看到的元素。一定要使用否定提示！

这里，模型应该将CFG 设置为 1，因此默认情况下负数信号不会工作，但有一个节点可以启用它们。使用方法很简单：打开管理器，输入kjnode，下载它，然后在你的工作流程中输入WAN Nag。这就是它的使用方法。将节点连接到你的 LoRA 加载器之后，使其与negative关联，最后将其放置在你的第一个 kSampler（high）中。

以下是针对不希望出现的移动的否定提示：
motion artifacts, animation artifacts, movement blur, motion distortion, dynamic distortion, shifting shapes, unstable render, instability, wobbling effect, jittering effect, vibrating render, inaccurate details, visual noise, distorted surfaces, rendering errors, warped shapes, exaggerated butt movement, jiggle, overanimated hips, unnatural butt motion, hyper bounce, extreme curves, distorted hips, unnatural pose, unrealistic anatomy, deformed body, disproportionate body, floating limbs, blurry textures, clipping, stretching, low detail, messy background, artifacts, butt bounce, moving hips, swinging hips, shaking butt, wiggling butt, moving lower body, moving pelvis, jiggling buttocks, bouncing butt, unstable stance, unnatural hip motion, exaggerated hip movement, hip sway, hip rotation, bottom motion, pelvis motion, wobbling hips, fidgeting lower body, dancing hips, pelvic movement, motion blur, unnatural movement

以下是来自 ComfyUI 官方工作流程的否定提示：
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

注意：如果您使用不带节点的默认工作流程，则此否定提示将不起作用。

作品参照

WAN 2.2 NF/SW 万相图生视频模型是一款基于 Wan Video 2.2 I2V-A14B 架构深度训练的专业级大模型，依托海量图像 - 视频配对数据与先进的时空建模技术，能够精准捕捉原图的细节特征与风格调性，高效生成流畅自然、风格统一的视频内容，适配多场景下的图生视频创作需求。

该模型用途广泛，但如有特定需求，请毫不犹豫地使用其他LoRa算法。同时，为了尽可能保留人脸特征，请适当降低LoRa算法的强度。

关于Fast Move V2版本

• 更好地理解
• 更好地理解相机
• 减少姿势之外不必要的前后移动
  （无法完全消除，但可大幅减少）
• 改善臀部弹跳效果
• 如果一名男子出现，他不会再自动试图在女子LT时与其发生关系。

这个版本是为那些想要更多动态场景和更多动作的用户设计的。

不同拍摄角度的示例提示

(at 0 seconds: wide frontal shot of a man standing in front of an open fridge, cinematic lighting, subtle ambient kitchen reflections, the fridge contents visible, camera static).
(at 1 second: medium shot from the front as he opens the fridge fully, reaches for a can, slight zoom-in to emphasize the action, cinematic framing).
(at 2 seconds: camera shifts to a side medium shot, tracking him as he lifts the can to his mouth, fluid movement, maintaining lighting and reflections).
(at 3 seconds: camera starts a smooth 360-degree orbit around the man, following him as he drinks from the can, motion fluid, background slightly blurred for cinematic effect).
(at 4 seconds: close-up on his face and upper body while drinking, orbit continues subtly, fridge reflections accentuating realism, cinematic polish).
(at 5 seconds: final wide shot as he lowers the can, camera completes orbit to original angle, showcasing the kitchen space, lighting, and dynamic movement).

可用的镜头运动

变焦/推拉

• zoom in
• zoom out
• camera zooms in on subject
• camera zooms out gradually
• dolly in
• dolly out
• camera dollies in slowly
• camera dollies out steadily
• crash zoom

平底锅

• pan left
• pan right
• camera pans across the scene
• gentle pan left
• sweeping pan right

倾斜

• tilt up
• tilt down
• camera tilts up to reveal…
• camera tilts down from…

轨道/跟踪/弧线/旋转

• orbit around subject
• 360° orbit
• camera circles around
• tracking shot
• camera tracks alongside subject
• arc shot
• curved camera movement

其他运动和风格

• static camera / static shot
• handheld shot
• camera roll

注意：
LoRA 与此模型完美兼容，在各种样式和概念中提供完全兼容性和一致的结果。

# 补充建议

不要犹豫使用否定提示。这在WAN视频中非常重要，它可以极大地改善您的视频质量，或者移除您不想看到的元素。一定要使用否定提示！

这里，模型应该将CFG 设置为 1，因此默认情况下负数信号不会工作，但有一个节点可以启用它们。使用方法很简单：打开管理器，输入kjnode，下载它，然后在你的工作流程中输入WAN Nag。这就是它的使用方法。将节点连接到你的 LoRA 加载器之后，使其与negative关联，最后将其放置在你的第一个 kSampler（high）中。

以下是针对不希望出现的移动的否定提示：
motion artifacts, animation artifacts, movement blur, motion distortion, dynamic distortion, shifting shapes, unstable render, instability, wobbling effect, jittering effect, vibrating render, inaccurate details, visual noise, distorted surfaces, rendering errors, warped shapes, exaggerated butt movement, jiggle, overanimated hips, unnatural butt motion, hyper bounce, extreme curves, distorted hips, unnatural pose, unrealistic anatomy, deformed body, disproportionate body, floating limbs, blurry textures, clipping, stretching, low detail, messy background, artifacts, butt bounce, moving hips, swinging hips, shaking butt, wiggling butt, moving lower body, moving pelvis, jiggling buttocks, bouncing butt, unstable stance, unnatural hip motion, exaggerated hip movement, hip sway, hip rotation, bottom motion, pelvis motion, wobbling hips, fidgeting lower body, dancing hips, pelvic movement, motion blur, unnatural movement

以下是来自 ComfyUI 官方工作流程的否定提示：
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

注意：如果您使用不带节点的默认工作流程，则此否定提示将不起作用。

作品参照

The two were French kissing, and the camera zoomed in on their faces.
Steps: 20, CFG scale: 1, Sampler: Euler a, Seed: -1

WAN 2.2 NF/SW 万相图生视频模型是一款基于 Wan Video 2.2 I2V-A14B 架构深度训练的专业级大模型，依托海量图像 - 视频配对数据与先进的时空建模技术，能够精准捕捉原图的细节特征与风格调性，高效生成流畅自然、风格统一的视频内容，适配多场景下的图生视频创作需求。

该模型用途广泛，但如有特定需求，请毫不犹豫地使用其他LoRa算法。同时，为了尽可能保留人脸特征，请适当降低LoRa算法的强度。

不同拍摄角度的示例提示

(at 0 seconds: wide frontal shot of a man standing in front of an open fridge, cinematic lighting, subtle ambient kitchen reflections, the fridge contents visible, camera static).
(at 1 second: medium shot from the front as he opens the fridge fully, reaches for a can, slight zoom-in to emphasize the action, cinematic framing).
(at 2 seconds: camera shifts to a side medium shot, tracking him as he lifts the can to his mouth, fluid movement, maintaining lighting and reflections).
(at 3 seconds: camera starts a smooth 360-degree orbit around the man, following him as he drinks from the can, motion fluid, background slightly blurred for cinematic effect).
(at 4 seconds: close-up on his face and upper body while drinking, orbit continues subtly, fridge reflections accentuating realism, cinematic polish).
(at 5 seconds: final wide shot as he lowers the can, camera completes orbit to original angle, showcasing the kitchen space, lighting, and dynamic movement).

可用的镜头运动

变焦/推拉

• zoom in
• zoom out
• camera zooms in on subject
• camera zooms out gradually
• dolly in
• dolly out
• camera dollies in slowly
• camera dollies out steadily
• crash zoom

平底锅

• pan left
• pan right
• camera pans across the scene
• gentle pan left
• sweeping pan right

倾斜

• tilt up
• tilt down
• camera tilts up to reveal…
• camera tilts down from…

轨道/跟踪/弧线/旋转

• orbit around subject
• 360° orbit
• camera circles around
• tracking shot
• camera tracks alongside subject
• arc shot
• curved camera movement

其他运动和风格

• static camera / static shot
• handheld shot
• camera roll

注意：
LoRA 与此模型完美兼容，在各种样式和概念中提供完全兼容性和一致的结果。

# 补充建议

不要犹豫使用否定提示。这在WAN视频中非常重要，它可以极大地改善您的视频质量，或者移除您不想看到的元素。一定要使用否定提示！

这里，模型应该将CFG 设置为 1，因此默认情况下负数信号不会工作，但有一个节点可以启用它们。使用方法很简单：打开管理器，输入kjnode，下载它，然后在你的工作流程中输入WAN Nag。这就是它的使用方法。将节点连接到你的 LoRA 加载器之后，使其与negative关联，最后将其放置在你的第一个 kSampler（high）中。

以下是针对不希望出现的移动的否定提示：
motion artifacts, animation artifacts, movement blur, motion distortion, dynamic distortion, shifting shapes, unstable render, instability, wobbling effect, jittering effect, vibrating render, inaccurate details, visual noise, distorted surfaces, rendering errors, warped shapes, exaggerated butt movement, jiggle, overanimated hips, unnatural butt motion, hyper bounce, extreme curves, distorted hips, unnatural pose, unrealistic anatomy, deformed body, disproportionate body, floating limbs, blurry textures, clipping, stretching, low detail, messy background, artifacts, butt bounce, moving hips, swinging hips, shaking butt, wiggling butt, moving lower body, moving pelvis, jiggling buttocks, bouncing butt, unstable stance, unnatural hip motion, exaggerated hip movement, hip sway, hip rotation, bottom motion, pelvis motion, wobbling hips, fidgeting lower body, dancing hips, pelvic movement, motion blur, unnatural movement

以下是来自 ComfyUI 官方工作流程的否定提示：
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

注意：如果您使用不带节点的默认工作流程，则此否定提示将不起作用。

作品参照

图片提示词

A beautiful girl with a pouty expression takes a drag from her cigarette then exhales smoke toward the viewer. Sensual and seductive scene.
Steps: 6, CFG scale: 1, Sampler: Euler

1. The woman uses her fork pick up some salad and eat a bite with her mouth. The woman eats  the salad with the fork, and swallows. The woman gags in disgust. she pushes the bowl of salad away out of view. looks straight at the camera. The woman's cheeks puff out as she gags in disgust.

2.The woman looks at the cake and changes her expression to a smile. She grabs a handful of cake with her hand.

3.The woman eats the cake. She is experiencing and orgasm.