FLUX_2_Klein_Multi_LoRA_infer – 6 MCP servers offer this tool

What it usually takes

  • custom_prompt_text – in 6 of 6
  • guidance_scale – in 6 of 6
  • lora_prompt_text – in 6 of 6
  • prompt – in 6 of 6
  • randomize_seed – in 6 of 6
  • seed – in 6 of 6
  • selected_titles – in 6 of 6
  • steps – in 6 of 6
  • upscale_factor – in 6 of 6
  • base_image – in 5 of 6
  • batch_count – in 5 of 6
  • batch_vary – in 5 of 6

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?
FLUX.2 Klein multi-LoRA co.huggingface.hittler-ai/flux.2-klein-multi-lora 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 toolbase_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_factorNot stated
FLUX.2 Klein multi-LoRA co.huggingface.cirujanoretro/flux.2-klein-multi-lora 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 toolbase_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_factorNot stated
FLUX.2 Klein multi-LoRA co.huggingface.yayite/flux.2-klein-multi-lora 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 toolbase_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_factorNot stated
FLUX.2 Klein multi-LoRA co.huggingface.masterp3000/flux.2-klein-multi-lora CPU-side wrapper — handles pre/post processing and logging. The actual GPU work is delegated to _infer_gpu so that the _spawn_log daemon thread survives after the @spaces.GPU subprocess exits. 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 toolcustom_prompt_text,guidance_scale,input_images,lora_prompt_text,param_10,param_11,param_12,param_13,param_14,param_15,prompt,randomize_seed,seed,selected_titles,steps,upscale_factorNot stated
FLUX.2 Klein multi-LoRA co.huggingface.gcc9/flux.2-klein-multi-lora 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 toolbase_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_factorNot stated
FLUX.2 Klein multi-LoRA co.huggingface.talkhan/flux.2-klein-multi-lora 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 toolbase_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_factorNot stated