Use Flux to generate initial images using the controlnet of your choice, then refine the images using WAN 2.2.
You will need this LORA. Clicking this link will download it. https://huggingface.co/Kijai/WanVideo_comfy/resolve/main/Lightx2v/lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank256_bf16.safetensors?download=true