Wan 2.2 LoRA Tutorial: The Easiest Way to Use LoRAs in ComfyUI — v1.0

Use this ComfyUI workflow to turn an image and text into a video with Wan Video 2.2 I2V-A14B; it uses the listed checkpoint, VAE, and LoRA files.

It loads and resizes the image, encodes it for image-to-video generation, applies text and LoRA conditioning, samples and decodes frames, and combines them into a video.

Provide an image and text; the workflow outputs a video assembled from decoded frames.

WanVideoDecode decodes the output frames, and VHS_VideoCombine combines them into a video.

This workflow is version v1.0 from Lordcaocao2025 and uses Wan Video 2.2 I2V-A14B.

The listed ComfyUI node packs are comfyui-kjnodes, comfyui-various, comfyui-videohelpersuite, and ComfyUI-WanVideoWrapper.

The listed model files are wan2.2_i2v_high_noise_14B_Q5_K_S.gguf, wan2.2_i2v_low_noise_14B_Q5_K_S.gguf, and wan_2.1_vae.safetensors.

The listed LoRA files are DestructiveKickHigh-000032.safetensors, DestructiveKickLow-000032.safetensors, and lightx2v_I2V_14B_480p_cfg_step_distill_rank64_bf16.safetensors.

Choose and apply LoRAs with WanVideoLoraSelect and WanVideoSetLoRAs.

Model, VAE, block-swap, and compile settings are handled by WanVideoModelLoader, WanVideoVAELoader, WanVideoBlockSwap, WanVideoSetBlockSwap, and WanVideoTorchCompileSettings.

Before use, verify that your ComfyUI setup includes the listed node packs and exact model and LoRA filenames.

Sugestão · não verificado

No separate description is provided for this workflow, so verify the image and text inputs, video output, and filenames against your setup before use.

Sugestão