The Git Repo is here: <a target="_blank" rel="ugc" href="https://github.com/therealkove-wq/img2imgVideoTransparency">https://github.com/therealkove-wq/img2imgVideoTransparency</a># img2img Transparent Video — ComfyUI WorkflowGenerates videos with a transparent background (WEBM + alpha channel) from a start and end frame using Wan 2.2 I2V with LightX2V LoRAs and rembg AI background removal.---## How it works1. You provide a start frame and an end frame (PNG images)2. The model generates the in-between frames3. rembg AI strips the background from every frame4. Output is a WEBM file with a real alpha channel, ready for compositing---## Required ModelsAll models are from [Comfy-Org/Wan_2.2_ComfyUI_Repackaged](<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged">https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged</a>) on HuggingFace.| File | Destination folder ||------|--------------------|| <code>wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors</code> | <code>ComfyUI/models/diffusion_models/</code> || <code>wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors</code> | <code>ComfyUI/models/diffusion_models/</code> || <code>wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors</code> | <code>ComfyUI/models/loras/wan/</code> || <code>wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors</code> | <code>ComfyUI/models/loras/wan/</code> || <code>umt5_xxl_fp8_e4m3fn_scaled.safetensors</code> | <code>ComfyUI/models/text_encoders/</code> || <code>wan_2.1_vae.safetensors</code> | <code>ComfyUI/models/vae/</code> |&gt; The workflow will show download buttons for missing models directly in ComfyUI.---## Custom Node SetupTwo custom node packages are required.### 1. wan_alpha_nodes (this repo)Provides the <code>SaveWebmWithAlpha</code> node used to export the final video.Copy the two files from this repo into ComfyUI:```ComfyUI/custom_nodes/wan_alpha_nodes/├── wan_alpha_<a target="_blank" rel="ugc" href="http://nodes.py">nodes.py</a>└── init.py```### 2. ComfyUI-rembgProvides the <code>RembgBackgroundRemover</code> node used for AI background removal. Install it via ComfyUI Manager or clone it into <code>ComfyUI/custom_nodes/</code>.---## Using the Workflow1. Open ComfyUI and load <code>kove_img_to_img_transparent.json</code>2. In the Start Frame node, upload your starting image3. In the End Frame node, upload your ending image4. Edit the Positive Prompt (see Prompting section below)5. In the WAN I2V Conditioning node, set width, height, and length (frame count)6. In the Save node, set your output filename and frame rate7. Click QueueThe output WEBM file will appear in <code>ComfyUI/output/</code>.---## Key Parameters| Parameter | Node | Notes ||-----------|------|-------|| Width / Height | WAN I2V Conditioning | Resolution of the output video. Default: 1024×1024 || Length | WAN I2V Conditioning | Number of frames. 61 frames @ 30 FPS ≈ 2 seconds || Filename | Save | Output file name. Existing files with the same name are overwritten without warning. || Frame Rate | Save | Playback FPS of the output WEBM || Codec | Save | VP8 (faster) or VP9 (better compression) || Quality | Save | 0–100. Default 20 is a good starting point |---## PromptingAlways include this phrase in the positive prompt:&gt; "The character is isolated against a transparent background."Without it, rembg has less context and background removal quality drops.The negative prompt is pre-filled with <code>blurry, distorted, low quality, static, no motion</code> — leave it as-is unless you have a specific reason to change it.### Example promptsIdle character animation```The character is isolated against a transparent background.The lighting is constant and even throughout the sequence.The character breathes gently and sways slightly from side to side.Hair and clothing move subtly with the sway.The character does not speak. Slow movements. Idle animation.```Floating object```The character is isolated against a transparent background.A glowing orb floats gently up and down. Soft pulsing light. Smooth looping motion.```Abstract effect```The character is isolated against a transparent background.Colorful particles swirl and drift slowly. Ethereal. Cinematic quality.```---## TroubleshootingNodes missing after loading the workflow- Confirm both custom node packages are installed and ComfyUI has been restarted- Check the ComfyUI console for import errorsBackground not fully removed- Make sure the transparent background phrase is in your positive prompt- Try a different rembg model in the <code>RembgBackgroundRemover</code> node (e.g. <code>isnet-anime</code> for illustrated characters)CUDA out of memory- Reduce width/height or frame count- The two diffusion models are large (14B fp8); 16GB+ VRAM recommendedOutput file is overwritten unexpectedly- Change the filename in the Save node before each runWEBM won't play in browser/editor- Switch codec to VP9 in the Save node for broader compatibility

Image to Image Video With Alpha Layer (WEBM format, wan2.2)

This updated version of the workflow vastly improves the image quality of the resulting film. Due to a bug in the Save node, the generated file was highly compressed of low quality. Now, the quality setting work, so you can produce uncompressed high quality films.# img2img Transparent Video — ComfyUI WorkflowGenerates videos with a transparent background (WEBM + alpha channel) from a start and end frame using Wan 2.2 I2V with LightX2V LoRAs and rembg AI background removal.---## How it works1. You provide a start frame and an end frame (PNG images)2. The model generates the in-between frames3. rembg AI strips the background from every frame4. Output is a WEBM file with a real alpha channel, ready for compositing---## Required ModelsAll models are from [Comfy-Org/Wan_2.2_ComfyUI_Repackaged](<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged">https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged</a>) on HuggingFace.| File | Destination folder ||------|--------------------|| <code>wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors</code> | <code>ComfyUI/models/diffusion_models/</code> || <code>wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors</code> | <code>ComfyUI/models/diffusion_models/</code> || <code>wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors</code> | <code>ComfyUI/models/loras/wan/</code> || <code>wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors</code> | <code>ComfyUI/models/loras/wan/</code> || <code>umt5_xxl_fp8_e4m3fn_scaled.safetensors</code> | <code>ComfyUI/models/text_encoders/</code> || <code>wan_2.1_vae.safetensors</code> | <code>ComfyUI/models/vae/</code> | &gt; The workflow will show download buttons for missing models directly in ComfyUI.---## Custom Node SetupTwo custom node packages are required.### 1. wan_alpha_nodes (this repo)Provides the <code>SaveWebmWithAlpha</code> node used to export the final video.Copy the two files from this repo into ComfyUI:```ComfyUI/custom_nodes/wan_alpha_nodes/├── wan_alpha_<a target="_blank" rel="ugc" href="http://nodes.py">nodes.py</a>└── init.py```### 2. ComfyUI-rembgProvides the <code>RembgBackgroundRemover</code> node used for AI background removal. Install it via ComfyUI Manager or clone it into <code>ComfyUI/custom_nodes/</code>.---## Using the Workflow1. Open ComfyUI and load <code>kove_img_to_img_transparent.json</code>2. In the Start Frame node, upload your starting image3. In the End Frame node, upload your ending image4. Edit the Positive Prompt (see Prompting section below)5. In the WAN I2V Conditioning node, set width, height, and length (frame count)6. In the Save node, set your output filename and frame rate7. Click QueueThe output WEBM file will appear in <code>ComfyUI/output/</code>.---## Key Parameters| Parameter | Node | Notes ||-----------|------|-------|| Width / Height | WAN I2V Conditioning | Resolution of the output video. Default: 1024×1024 || Length | WAN I2V Conditioning | Number of frames. 61 frames @ 30 FPS ≈ 2 seconds || Filename | Save | Output file name. Existing files with the same name are overwritten without warning. || Frame Rate | Save | Playback FPS of the output WEBM || Codec | Save | VP8 (faster) or VP9 (better compression) || Quality | Save | 0–100. Default 20 is a good starting point |---## PromptingAlways include this phrase in the positive prompt:&gt; "The character is isolated against a transparent background."Without it, rembg has less context and background removal quality drops.The negative prompt is pre-filled with <code>blurry, distorted, low quality, static, no motion</code> — leave it as-is unless you have a specific reason to change it.### Example promptsIdle character animation```The character is isolated against a transparent background.The lighting is constant and even throughout the sequence.The character breathes gently and sways slightly from side to side.Hair and clothing move subtly with the sway.The character does not speak. Slow movements. Idle animation.```Floating object```The character is isolated against a transparent background.A glowing orb floats gently up and down. Soft pulsing light. Smooth looping motion.```Abstract effect```The character is isolated against a transparent background.Colorful particles swirl and drift slowly. Ethereal. Cinematic quality.```---## TroubleshootingNodes missing after loading the workflow- Confirm both custom node packages are installed and ComfyUI has been restarted- Check the ComfyUI console for import errorsBackground not fully removed- Make sure the transparent background phrase is in your positive prompt- Try a different rembg model in the <code>RembgBackgroundRemover</code> node (e.g. <code>isnet-anime</code> for illustrated characters) CUDA out of memory- Reduce width/height or frame count- The two diffusion models are large (14B fp8); 16GB+ VRAM recommendedOutput file is overwritten unexpectedly- Change the filename in the Save node before each runWEBM won't play in browser/editor- Switch codec to VP9 in the Save node for broader compatibility

imageToImageVideoWithAlpha_v12.json

v1.2

v1.1

v1.0

Added node for color correction to mitigate light flicker and sudden color changes.

Files with SHA256: a0a4986271bb4a7b5a697c745213e14c9a5b5fd99ee5c2536685afd3c0e21429