FLUX_2_Klein_Multi_LoRA_v2_bulk_infer – 1 MCP server offers this tool
What it usually takes
canvas_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 1input_files– in 1 of 1lora_prompt_text– in 1 of 1pad_color– in 1 of 1param_16– in 1 of 1param_17– in 1 of 1param_18– 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 Process each uploaded image as its own GPU call, streaming results into the bulk output gallery as soon as they complete. Outputs and a CSV manifest are written to /tmp/bulk_<sid>/ with stable filenames, so a ZeroGPU quota wall mid-run still leaves earlier outputs grabbable from the gallery and from disk. Logging: each image is logged individually via _spawn_log on success or failure — same code path as single/batch, so bulk shows up in the dataset with the same schema, just with extra bulk_index / bulk_total fields embedded in the PNG metadata. 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 | canvas_fit_mode,canvas_mode,custom_height,custom_prompt_text,custom_width,guidance_scale,input_files,lora_prompt_text,pad_color,param_16,param_17,param_18,param_19,param_20,param_21,prompt,randomize_seed,seed,selected_titles,steps,upscale_factor | Not stated |