WAN-KR (WAN 2.2 I2V workflow) — v3.9
Added slider for upscale (1.25x - 4x in 0.25 steps)
Runtime profile
- Access
- External workflow
- Status
- Listed
- Version
- WAN-KR_II_v3.9.json
- Source
- Civitai
- Updated
- Nov 3, 2026
Source description
Added optional TorchCompile toggle
Added slider for upscale (1.25x - 4x in 0.25 steps)
Some layout resizing due to new ComfyUI workflow row change (w*nkers)
Layout change to display the endframe
What you need
- Model files
- 1.2 GiB known subtotal
Remaining hardware or download-size estimates are not available yet.
Requirements
Models
124x_NMKD-Superscale-SP_178000_G.pth
Not resolvedOptionalUpscaler · Unknown
clip_vision_h.safetensors
Not resolvedClip Vision · Unknown
film_net_fp32.pt
Not resolvedCheckpoint · Unknown
LoRA · 704 MB · SAFETENSOR · Unknown
- Found
Checkpoint · 20.4 MB · PTH · Unknown
umt5_xxl_fp16.safetensors
PossibleText encoder · Unknown
Wan2_1_VAE_fp32.safetensors
Not resolvedVAE · Unknown
wan2.2_i2v_high_noise_14B_Q8_0.gguf
Not resolvedCheckpoint · Unknown
wan2.2_i2v_low_noise_14B_Q8_0.gguf
Not resolvedCheckpoint · Unknown
LoRA · 585 MB · SAFETENSORS · FP16 (unverified) · Unknown
LoRA · 585 MB · SAFETENSORS · FP16 (unverified) · Unknown
LoRA · 708 MB · SAFETENSORS · Unknown
Node packs
10ComfyUI_Comfyroll_CustomNodes
FoundOptionalNode pack · Registry
comfyui-frame-interpolation
FoundNode pack · Registry
comfyui-kjnodes
FoundNode pack · Registry
comfyui-mxtoolkit
FoundNode pack · Registry
comfyui-videohelpersuite
FoundNode pack · Registry
Fast Groups Bypasser (rgthree)
Not resolvedNode pack · Unknown
Fast Groups Muter (rgthree)
Not resolvedNode pack · Unknown
gguf
PossibleNode pack · Registry
rgthree-comfy
FoundNode pack · Registry
torchcompilemodel_lorasafe
FoundNode pack · Registry
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Purpose
WAN-KR (WAN 2.2 I2V workflow) is a ComfyUI workflow for Wan Video 2.2 I2V work. It organizes elements to reduce scrolling and panning, uses a JSON file with custom dimensions for setup, and has no specified runtime input or output fields.
Inputs and outputs
The named setup input is a JSON file with custom dimensions; runtime input and output fields are not specified.
Setup
Place the JSON file with custom dimensions in ComfyUI\custom_nodes\comfyui-kjnodes\.
Dependencies
Named node packs include ComfyUI_Comfyroll_CustomNodes, ComfyUI-Frame-Interpolation, ComfyUI-KJNodes, ComfyUI-mxToolkit, ComfyUI-VideoHelperSuite, gguf, rgthree-comfy, and TorchCompileModel_LoRASafe.
Named model files include wan2.2_i2v_high_noise_14B_Q8_0.gguf, wan2.2_i2v_low_noise_14B_Q8_0.gguf, clip_vision_h.safetensors, umt5_xxl_fp16.safetensors, and Wan2_1_VAE_fp32.safetensors.
Additional named files are 4x_NMKD-Superscale-SP_178000_G.pth, film_net_fp32.pt, and rife49.pth.
Configuration
The layout groups elements to reduce scrolling and panning.
For V3.9, the sizes were updated for a GUI change that adds another workflow row.
The TorchCompile node is from TorchCompileModel_LoRASafe, and the workflow notes that another compile node should work too.
Cautions
Before use, verify that rife49.pth, film_net_fp32.pt, and Wan2_1_VAE_fp32.safetensors are available under those exact filenames.
Suggestion · not verified
If you plan to use the described GGUF Q8 setup, check hardware capacity first: it may use all VRAM on a 4090 and 64(+) RAM.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 source
Sources
1 sourceDownload files
Model artifacts
2 artifacts
Model artifacts
2 artifactsSource excerpts
3 excerpts
Source excerpts
3 excerptsSource context: 342 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
Source context: 324 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
Source context: 292 downloads · Type Workflows · Base model Wan Video 2.2 I2V-A14B
