WAN 2.2 I2V - Simple multiple prompt/video loop — v1.0

Use WAN 2.2 I2V - Simple multiple prompt/video loop to create 1–10 stitched videos from models, optional LoRAs, a first-frame image, image size, video length, and prompts separated by “|”; each video passes its last frame to the next.

Load the models, optionally load LoRAs, add the first-frame image, and set the image size and video length.

Separate prompts with “|” to generate multiple videos using the previous video’s last frame, then stitch the videos together.

Inputs are models, optional LoRAs, a first-frame image, image size, video length, and prompts separated by “|”.

The output is 1–10 stitched videos, with each later video using the previous video’s last frame as its first-frame input.

The listed base model is Wan Video 14B i2v 720p, and the publisher is Yorgash.

No license is listed.

The listed node packs are: comfyui_essentials, comfyui_llm_party, comfyui_tinyterranodes, ComfyUI-Crystools, comfyui-easy-use, comfyui-kjnodes, ComfyUI-QualityOfLifeSuit_Omar92, and mikey_nodes.

Before using it, verify that your setup has these model files: CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, wan_2.1_vae.safetensors, wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors, and wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors.

Vorschlag

The listed LoRA files are: Wan21_AccVid_I2V_480P_14B_lora_rank32_fp16.safetensors and Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64_fixed.safetensors.

Use “|” between prompts to generate multiple videos connected through the previous video’s last frame.

Motion may be lost between clips because no VACE model of 2.2 is currently available.