Wan 2.2 S2V Speech to Video 5 Steps #ComfyUI Native Workflow + Step by Step #s2v #wan22 #lipsync#ai

This ComfyUI workflow is for Wan 2.2 speech-to-video generation. It takes speech as input and produces video.

The core task is speech-to-video, with speech as the input and video as the output.

Raretutor publishes it, and its base model is Wan Video 2.2 I2V-A14B.

It is presented as a ComfyUI Native Workflow with step-by-step guidance and a direction to download all models.

Listed node packs are comfyui_essentials, comfyui-kjnodes, ComfyUI-MelBandRoFormer, comfyui-multigpu, gguf, image-saver, and soundflow.

Listed model files include lightx2v_I2V_14B_480p_cfg_step_distill_rank32_bf16.safetensors, MelBandRoformer_fp16.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, umt5-xxl-encoder-Q6_K.gguf, WAN_2_1_VAE_bf16.safetensors, and WAN_pig_wan_vae_fp32-f32.gguf.

Other listed model files are Wan2_2-S2V-14B_fp8_e4m3fn_scaled_KJ.safetensors, wan2.2_t2v_lightx2v_4steps_lora_v1.1_high_noise.safetensors, Wan2.2-Lightning_I2V-A14B-4steps-lora_HIGH_fp16.safetensors, Wan2.2-Lightning_I2V-A14B-4steps-lora_LOW_fp16.safetensors, wan2.2-s2v-14b-q5_0,

Before use, verify that these model files are present and match your setup: lightx2v_I2V_14B_480p_cfg_step_distill_rank32_bf16.safetensors, MelBandRoformer_fp16.safetensors, umt5_xxl_fp8_e4m3fn_scaled.safetensors, umt5-xxl-encoder-Q6_K.gguf, WAN_2_1_VAE_bf16.safetensors, WAN_pigワ

Suggestion · non vérifié

Also verify that the soundflow and image-saver node packs are available before use.

Suggestion · non vérifié