LTX_2_5_run – 4 MCP servers offer this tool
What it usually takes
auto_len– in 3 of 4decoder– in 3 of 4do_enhance– in 3 of 4duration_s– in 3 of 4height– in 3 of 4image_path– in 3 of 4prompt– in 3 of 4randomize_seed– in 3 of 4seed– in 3 of 4width– in 3 of 4json_params– in 1 of 4
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? |
|---|---|---|
LTX-2.5 co.huggingface.lightricks/ltx-2.5 CPU step (enhance, seed) then the GPU step, so the GPU is not held during enhancement. 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 | auto_len,decoder,do_enhance,duration_s,height,image_path,prompt,randomize_seed,seed,width | Not stated |
LTX-2.5 co.huggingface.rioshiina/ltx-2.5 [Recommended Flow Step 2] Unified video generation task execution interface (t2v, i2v, flf2v, ta2v, ia2v). Accepts a JSON string or dict of parameters. REQUIRED PARAMETERS PER TASK TYPE: - t2v: task_type, prompt, duration - i2v: task_type, prompt, start_image, duration - flf2v: task_type, prompt, start_image, end_image, duration - ta2v: task_type, prompt, audio_file - ia2v: task_type, prompt, start_image, audio_file GLOBAL OPTIONAL CONTROL PARAMETERS: - seed (int): Random seed (-1 for random, >=0 for deterministic reproducibility). Default: -1. - zero_gpu_duration (int): GPU quota allocation in seconds on HuggingFace ZeroGPU spaces (default: 60). - use_spatial_upscaler (bool): Whether to enable 2x spatial upscaling (default: false). - use_temporal_upscaler (bool): Whether to enable 2x temporal upscaling (default: false). | json_params | Not stated |
LTX-2.5 Video + Audio co.huggingface.elanthendral/ltx-2.5 Generate a short video with synchronized audio from a text prompt, optionally animating an input image (image-to-video). 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 mp4 path, the prompt actually used, the seed used, and the generated length. | auto_len,decoder,do_enhance,duration_s,height,image_path,prompt,randomize_seed,seed,width | Not stated |
LTX-2.5 co.huggingface.x-highvoltage-x/ltx-2.5 CPU step (enhance, seed) then the GPU step, so the GPU is not held during enhancement. 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 | auto_len,decoder,do_enhance,duration_s,height,image_path,prompt,randomize_seed,seed,width | Not stated |