Video from a picture on WanVideoWrapper

<!-- lesson: wrapper-image -->

Lesson "wrapper-image", in the group WanVideoWrapper of the lesson list. Steps: 8.

#What you will be able to do

A clip made on WanVideoWrapper nodes starts from your picture.

#What you need

• It goes on from Video on WanVideoWrapper. The card says so; it is a hint, not a lock.
• Model files the lesson checks:
  • the high_noise half of Wan 2.2 image to video (i2v): models/diffusion_models, for example wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors;
  • the low_noise half of Wan 2.2 image to video (i2v): models/diffusion_models, for example wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors.
• Nodes: WanVideo Model Loader, WanVideo VAE Loader, WanVideo Sampler, Load Image, WanVideo ImageToVideo Encode.
• The app downloads and installs nothing. The step texts below say which files and folders, and which ComfyUI template names them.

#The steps

The words of each step, as the lesson shows them. Node names are in bold.

1. What changes (reading)

   The graph is the one from "Video on WanVideoWrapper". Three things change: the model files, a node with the picture, and a node that puts the picture at the start of the clip in place of the empty blank.

2. A WanVideoWrapper graph is needed

   This lesson goes on from the graph of "Video on WanVideoWrapper". The canvas must have two WanVideo Model Loader loaders, a WanVideo VAE Loader node and two WanVideo Sampler samplers, the second taking the result of the first.

   If they are not there, do that lesson first.

3. Models for a picture

   In the model field of both loaders choose i2v files: one with high_noise in its name, the other with low_noise.

   The t2v models do not take a picture. The rest of the graph stays as it is.

4. Load the picture

   Add a Load Image node and choose your picture in its image field. The list shows the files of the input folder of your ComfyUI.

5. Prepare the start

   Add a WanVideo ImageToVideo Encode node and connect to it:

   • to vae, the output of WanVideo VAE Loader;
   • to start_image, the IMAGE output of Load Image.

   Set width to 832, height to 480 and num_frames to 81. Proportions like those of the picture work best.

6. Connect the start to the samplers

   Connect the image_embeds output of WanVideo ImageToVideo Encode to the image_embeds input of both samplers.

   The old links from the empty blank come off by themselves. The empty blank node can be deleted after that.

7. How to get more motion (reading)

   If the clip hardly moves, WanVideo ImageToVideo Encode has two fields that change that:

   • noise_aug_strength: a little noise over the picture, for example 0.02, gives the model freedom to move;
   • start_latent_strength: a value below 1, for example 0.8, holds the first frame less.

   Change one field at a time. Values too large take the clip away from the picture.

   The node also has an end_image input: a picture for the last frame. It needs models trained for it. The model's page says whether it can.

8. The graph is ready (reading)

   Save the graph with "File ▸ Save workflow for ComfyUI…", open the file in ComfyUI and run it there. This app runs nothing in ComfyUI itself.

   The prompt of a clip from a picture says what changes, not what is already seen. More on this in "A prompt for video".

#What the lesson checks

A reading step is done when you press Got it, next. A doing step ticks itself off when the canvas holds:

• Step 2, A WanVideoWrapper graph is needed:
  • a WanVideo Model Loader node.
  • a WanVideo Model Loader node.
  • a WanVideo VAE Loader node.
  • a WanVideo Sampler node.
  • a WanVideo Sampler node.
  • model of WanVideo Model Loader (first pass) into model of WanVideo Sampler (first pass).
  • model of WanVideo Model Loader (second pass) into model of WanVideo Sampler (second pass).
  • samples of WanVideo Sampler (first pass) into samples of WanVideo Sampler (second pass).
• Step 3, Models for a picture:
  • model of WanVideo Model Loader (first pass) holds the high_noise half of Wan 2.2 image to video (i2v); such a file lies in models/diffusion_models, for example wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors.
  • model of WanVideo Model Loader (second pass) holds the low_noise half of Wan 2.2 image to video (i2v); such a file lies in models/diffusion_models, for example wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors.
• Step 4, Load the picture:
  • a Load Image node.
  • image of Load Image: a value is chosen.
• Step 5, Prepare the start:
  • a WanVideo ImageToVideo Encode node.
  • vae of WanVideo VAE Loader into vae of WanVideo ImageToVideo Encode.
  • IMAGE of Load Image into start_image of WanVideo ImageToVideo Encode.
  • num_frames of WanVideo ImageToVideo Encode is from 49 to 121, a frame count of the form 4n + 1; Do this for me sets 81. Why: wan takes a number of frames of the form 4n + 1: 49, 81, 121. 81 frames at 16 per second make five seconds.
• Step 6, Connect the start to the samplers:
  • image_embeds of WanVideo ImageToVideo Encode into image_embeds of WanVideo Sampler (first pass).
  • image_embeds of WanVideo ImageToVideo Encode into image_embeds of WanVideo Sampler (second pass).

#Mistakes people make

• Leaving one sampler on the empty embeds.
• Raising both motion fields at once: the clip drifts away from the picture.

#See also

• How lessons work
• Lesson: Video from a picture
• First and last frame
• Video models