ae_minimax_h3_video_generate
Generate a video with audio using MiniMax H3. A text prompt is required. For text-to-video, omit both image URLs. To guide the opening frame, provide a public HTTPS URL in `image_url`. You can also provide a public HTTPS URL in `end_image_url` to guide the final frame, but a final image alone is not supported.
Choose a duration of 5–15 whole seconds (default: 5), a resolution tier of 480P, 768P, 1080P, 2K, or 4K (default: 2K), and an aspect ratio of 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16 (default: 16:9). You can optionally set `seed` to a nonnegative safe integer (0–9,007,199,254,740,991). Resolution tiers do not guarantee exact pixel dimensions, and a fixed seed does not guarantee frame-by-frame reproducibility.
Submission returns a task ID. Use it with `ae_get_result` to check progress and retrieve the video URL when the task completes.
ae_dataforseo_ai_optimization_perplexity_llm_responses_live
Generate a response from a Perplexity model through DataForSEO. Provide the task parameters in the request_body array according to this interface schema.
ae_birefnet_v2
ae_birefnet_v2 — Image Background Removal
Remove the background from an image URL to create a subject cutout using Bria through WaveSpeed. Supply the URL in request_body.image; results become available when asynchronous processing completes. The tool identifier is retained, but the current model is Bria, not BiRefNet. No additional processing controls are exposed.
ae_hunyuan_image_3_instruct_gpu
Create images from text prompts with selectable size, format, and number of results.
ae_aura_sr
ae_aura_sr — Image Upscaling
Upscale an image from a URL using WaveSpeed's image-upscaler service. Choose a target resolution of 2K, 4K, or 8K (default 4K) and JPEG, PNG, or WebP output (default JPEG). Processing is asynchronous. The tool identifier is retained, but the service does not use the AuraSR model.
ae_firered_image_edit_v1_1
Edit one or more images with a written instruction, including virtual try-ons, style changes, and portrait makeup.
ae_qwen_image_edit_plus_lora
Edit one or more images with text instructions, including optional style controls, negative prompts, output sizing, and multiple variations.
ae_bria_fibo_generate
Create images from a text description or reference image. Control the style, composition, lighting, objects, aspect ratio, resolution, and content to avoid.
ae_flux_2_pro_edit
Modify existing images using a written instruction. Choose the output size and JPEG or PNG format.
ae_fast_lightning_sdxl
ae_fast_lightning_sdxl — Generate images with WaveSpeed Z-Image-Turbo from a text prompt, optionally guided by a reference image URL. Set the output size, JPEG/PNG/WebP format, seed, and transformation strength; higher strength produces a result more different from the reference. Generation runs asynchronously, with results retrieved after completion. The retained tool identifier does not indicate the model: this tool uses Z-Image-Turbo, not SDXL, and supports only the controls in the current input schema.
ae_drct_super_resolution
Upscale an image by a selected multiplier to make it larger and higher resolution.
ae_pixverse_c1_transition
Create a prompt-guided video that transitions from a starting image to a required ending image. Control the duration, aspect ratio, resolution, and optional audio.
ae_codeformer
Restore and enhance faces in photos, with options for face alignment, facial upscaling, and detail preservation.
ae_qwen_image_edit_inpaint
Edit selected parts of an image by filling a masked area with content described in a text prompt.
ae_flux_kontext_lora_inpaint
Edit selected areas of an image using a mask, text instructions, and a reference image while preserving the rest.
ae_recraft_v4_pro_text_to_image
Create professional design and marketing images from text prompts, with custom dimensions, background color, and preferred color palette controls.