plug.directory
Add my server

lenovo_qwen_image_2_1_lora_generate

1 MCP server offers this tool

What it usually takes

  • aspect_ratio – in 1 of 1
  • compare_base – in 1 of 1
  • lora_strength – in 1 of 1
  • num_inference_steps – in 1 of 1
  • prompt – in 1 of 1
  • randomize_seed – in 1 of 1
  • resolution – in 1 of 1
  • seed – 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

ServerInputsRead-only?
l3n0v0 - Lenovo style LoRA for Qwen-Image-2.1 co.huggingface.hugging-apps/lenovo-qwen-image-2-1-lora Generate an image in the LoRA's style. Validation and trigger-word injection deliberately happen here, in the main process: a rejected prompt must never reserve a GPU slot, and gr.Error raised inside the ZeroGPU worker reaches the browser as a bare "RuntimeError" instead of its message. Gradio only binds a live gr.Progress to the function it calls, which is this one — the copy in _generate's signature is an inert import-time default — so it is forwarded positionally.aspect_ratio,compare_base,lora_strength,num_inference_steps,prompt,randomize_seed,resolution,seedNot stated