FLUX_2_Klein_Multi_LoRA_v2_infer – 1 MCP server offers this tool
What it usually takes
base_image– in 1 of 1batch_count– in 1 of 1batch_vary– in 1 of 1canvas_fit_mode– in 1 of 1canvas_mode– in 1 of 1custom_height– in 1 of 1custom_prompt_text– in 1 of 1custom_width– in 1 of 1guidance_scale– in 1 of 1lora_prompt_text– in 1 of 1pad_color– in 1 of 1param_21– 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? |
|---|---|---|
FLUX.2 Klein Multi LoRA V2 co.huggingface.m3st3rj4k3l/flux.2-klein-multi-lora-v2 Generator. Streams a list of PNG paths into the output gallery, one result at a time. Each iteration is its own @spaces.GPU call, so a ZeroGPU quota wall mid-batch only loses the in-progress item — earlier PNGs are already saved to disk and surfaced in the gallery. 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 | base_image,batch_count,batch_vary,canvas_fit_mode,canvas_mode,custom_height,custom_prompt_text,custom_width,guidance_scale,lora_prompt_text,pad_color,param_21,param_22,param_23,param_24,param_25,param_26,prompt,randomize_seed,reference_images,seed,selected_titles,steps,sweep_max,sweep_min,upscale_factor | Not stated |