ae_demucs
Separate a mixed audio file into stems such as vocals, drums, bass, guitar, piano, and other instruments.
AgentEarth Tool Catalog
Leading image, video and other generation tools, including GPT-Image2, NanoBanana and Seedance, are ready to use in one place at better prices.
Tool List
ae_demucs
Separate a mixed audio file into stems such as vocals, drums, bass, guitar, piano, and other instruments.
ae_fast_sdxl_image_to_image
ae_fast_sdxl_image_to_image — Transform a reference image with a text prompt using WaveSpeed Z-Image-Turbo Image-to-Image. Provide an image URL and prompt; optionally set transformation strength, output size (width*height), JPEG/PNG/WebP format, and seed. Higher strength changes the reference image more. Generation runs asynchronously. The tool identifier is retained, but the current model is not SDXL and legacy SDXL-specific or advanced controls are not supported.
ae_image_editing_text_removal
Remove text, watermarks, or logos from an image and fill the area to blend with the surrounding background.
ae_seedvr_upscale_image
Increase an image's resolution by a chosen scale factor or target resolution, with options for output format and noise level.
ae_z_image_base
Generate one or more images from a text prompt, with options for size, format, and details to avoid.
ae_kling_video_o3_pro_image_to_video
Turn a starting image into a 3-15 second video with a text prompt, optional ending image, multi-shot scenes, and generated audio.
ae_ideogramai_post_generate_image_v_3
Generate one or more images from a detailed text prompt with Ideogram 3.0. Choose an aspect ratio or resolution, and optionally add styles, reference images, color palettes, negative prompts, rendering speed, or a seed for reproducible results. Download images you want to keep because the links expire.
ae_ip_adapter_face_id
ae_ip_adapter_face_id — Generate an image with WaveSpeed FLUX-PuLID from a text prompt and one reference image, aiming to carry the reference face's likeness into the result. Provide prompt and image in request_body. Optional settings include output size, guidance scale, seed, and JPEG, PNG, or WebP format. Processing is asynchronous; retain the returned task ID to check status and retrieve outputs. The tool identifier is retained, but the current model is FLUX-PuLID, not the original IP-Adapter or legacy SDXL/Kolors models. Only current schema settings are supported; multiple reference images, mixed identities, and exact likeness are not guaranteed.
ae_phota
Create up to four photorealistic images from a text prompt, with optional profile references, framing, high resolution, and file format choices.
ae_minimax_image_01
Generate one or more images from a text description with your chosen aspect ratio.
ae_hy_wu_edit
Edit images using written instructions and up to three reference images, such as changing outfits or combining visual elements.
ae_pulid
ae_pulid — Generate portraits or other images from a reference image and a text prompt using WaveSpeed FLUX-PuLID. The reference guides the subject's likeness; an exact match is not guaranteed. Provide both the reference image and prompt. You can optionally set image size, guidance scale, seed, and output format (JPEG, PNG, or WebP). Generation runs asynchronously, and the result is retrieved for the submitted task.
ae_flux_pulid
Create images from a text prompt while preserving the identity of a person in a reference image.
ae_bria_background_remove
Remove an image background and create a transparent cutout of the foreground subject.
ae_flux_lora
Generate images from a text prompt with optional custom style, character, or concept weights.
ae_lyria3
Generate a 30-second music clip from a text prompt, optionally guided by an image. Returns an AE task ID; query status and results with ae_get_result. Lyria 3 does not support negative_prompt. Omit this parameter; only an empty string is retained for legacy compatibility. Do not send a non-empty negative_prompt.