This ComfyUI tutorial workflow shows how to perform fast, instruction-based image edits using Qwen-Image-Edit-2511. It wires a simple I/O path—LoadImage (or VHS_LoadVideo for frames) into a compact Subgraph node (ID cdb2cf24-c432-439b-b5c8-5f69838580c9)—and ends with SaveImage. Inside the subgraph, the edit is driven by the Qwen 2.5 VL text encoder (qwen_2.5_vl_7b_fp8_scaled.safetensors) and a lightweight LoRA tuned for speed (Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors). The subgraph encapsulates the model plumbing so you can focus on a plain-language instruction like “make the sky overcast” or “remove the background,” then preview results quickly.

Technically, the workflow routes your source image (or video frames) into the subgraph, where the Qwen 2.5 VL encoder interprets your instruction text and conditions the edit. The Qwen-Image-Edit-2511 Lightning LoRA applies the learned edit behavior while keeping inference fast with very few sampling steps. Because this is packaged as a Subgraph, you get a clean graph and consistent defaults—you can double-click or open the subgraph to inspect or tweak internals as needed. SaveImage captures each result frame to disk; when fed by VHS_LoadVideo, you’ll get a numbered image sequence you can reassemble externally if you want a final video.