【WAN】TXT to IMAGE — v2.0

【WAN】TXT to IMAGE is a ComfyUI workflow for generating images from a text prompt and a WAN model, with optional SeedVR2 upscaling and generation-parameter metadata in the saved image.

Load a WAN model, enter a text prompt, and generate an image.

In the auto version, models can download automatically, and saved images can include all generation parameters in their metadata.

Inputs: a text prompt and a WAN model. Output: a generated image.

The image can also include SeedVR2 tiled upscaling and generation-parameter metadata.

In ComfyUI Settings, enable “Use Nodes V2 (Vue),” refresh the page, and then load the workflow.

Install ComfyUI-UmeAiRT-Toolkit through ComfyUI Manager by searching “UmeAiRT,” or use the UmeAiRT Auto-Installer.

Before use, check that comfyui-umeairt-toolkit and WAN_2.2/T2V are available.

Suggestion · not verified

If you use the upscaling options, check for 4x_NMKD-Siax_200k.pth and seedvr2_ema_3b_fp8_e4m3fn.safetensors.

Suggestion · not verified

For manual setup, the listed files include CLIP umt5_xxl_fp8_e4m3fn_scaled.safetensors, VAE wan_2.1_vae.safetensors, Speed LoRA lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank64_bf16.safetensors, and RealESRGAN_x4plus.pth or RealESRGAN_x4plus_anime_6B.pth for upscaling.

Toggle the built-in SeedVR2 upscaler on or off.

Use three LoRA slots with individual on/off toggles and strength controls; additional LoRA modules can be connected.

The listed base model is Wan Video 2.2 T2V-A14B.

Enable “Use Nodes V2 (Vue)” before loading; otherwise, the workflow may have display problems.