qwen_image_2_1_generate_image – 1 MCP server offers this tool
What it usually takes
aspect_ratio– in 1 of 1input_images– in 1 of 1negative_prompt– in 1 of 1num_inference_steps– in 1 of 1prompt– in 1 of 1resolution– in 1 of 1seed– in 1 of 1true_cfg_scale– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
Qwen-Image-2.1 co.huggingface.hugging-apps/qwen-image-2-1 Generate or edit an image with Qwen-Image-2.1. With no input images this is text-to-image; with one to ten input images it is image editing, and the prompt may refer to them as <image1>…<image10>. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: The generated image, as RGBA (the model natively supports transparency). | aspect_ratio,input_images,negative_prompt,num_inference_steps,prompt,resolution,seed,true_cfg_scale | Not stated |