Gemini Omni Flash 1.2
Text to video · Image to video · Video editing
Starting price $0.0433 / second
By Alibaba
Guide a video edit with a source clip, a mask or reference images in Wan VACE 14B. Use the prompt to describe what changes in the part you are editing.
wan-vace-14bQuote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-vace-14b",
"input": {
"prompt": "A knight in silver armor walks through a misty forest at dawn, following the movement and camera path of the source video."
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "wan-vace-14b", "quote_id": "QUOTE_ID", "input": {"prompt":"A knight in silver armor walks through a misty forest at dawn, following the movement and camera path of the source video."}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
promptrequired | string | The text prompt to guide video generation. |
negative_prompt | string | Negative prompt for video generation. |
match_input_num_frames | boolean | If true, the number of frames in the generated video will match the number of frames in the input video. If false, the number of frames will be determined by the num_frames parameter. |
num_frames | integer | Number of frames to generate. Must be between 81 to 241 (inclusive). |
match_input_frames_per_second | boolean | If true, the frames per second of the generated video will match the input video. If false, the frames per second will be determined by the frames_per_second parameter. |
frames_per_second | integer | Frames per second of the generated video. Must be between 5 to 30. Ignored if match_input_frames_per_second is true. |
task | string (enum) | Task type for the model. |
seed | integer | Random seed for reproducibility. If None, a random seed is chosen. |
resolution | string (enum) | Resolution of the generated video. |
aspect_ratio | string (enum) | Aspect ratio of the generated video. |
num_inference_steps | integer | Number of inference steps for sampling. Higher values give better quality but take longer. |
guidance_scale | number | Guidance scale for classifier-free guidance. Higher values encourage the model to generate images closely related to the text prompt. |
sampler | string (enum) | Sampler to use for video generation. |
shift | number | Shift parameter for video generation. |
video_url | string (URL) | URL to the source video file. If provided, the model will use this video as a reference. |
mask_video_url | string (URL) | URL to the source mask file. If provided, the model will use this mask as a reference. |
mask_image_url | string (image URL) | URL to the guiding mask file. If provided, the model will use this mask as a reference to create masked video. If provided mask video url will be ignored. |
ref_image_urls | array of image URLs | URLs to source reference image. If provided, the model will use this image as reference. |
first_frame_url | string (image URL) | URL to the first frame of the video. If provided, the model will use this frame as a reference. |
last_frame_url | string (image URL) | URL to the last frame of the video. If provided, the model will use this frame as a reference. |
enable_prompt_expansion | boolean | Whether to enable prompt expansion. |
preprocess | boolean | Whether to preprocess the input video. |
acceleration | string (enum) | Acceleration to use for inference. Options are 'none' or 'regular'. Accelerated inference will very slightly affect output, but will be significantly faster. |
video_quality | string (enum) | The quality of the generated video. |
video_write_mode | string (enum) | The write mode of the generated video. |
num_interpolated_frames | integer | Number of frames to interpolate between the original frames. A value of 0 means no interpolation. |
temporal_downsample_factor | integer | Temporal downsample factor for the video. This is an integer value that determines how many frames to skip in the video. A value of 0 means no downsampling. For each downsample factor, one upsample factor will automatically be applied. |
enable_auto_downsample | boolean | If true, the model will automatically temporally downsample the video to an appropriate frame length for the model, then will interpolate it back to the original frame length. |
auto_downsample_min_fps | number | The minimum frames per second to downsample the video to. This is used to help determine the auto downsample factor to try and find the lowest detail-preserving downsample factor. The default value is appropriate for most videos, if you are using a video with very fast motion, you may need to increase this value. If your video has a very low amount of motion, you could decrease this value to allow for higher downsampling and thus longer sequences. |
interpolator_model | string (enum) | The model to use for frame interpolation. Options are 'rife' or 'film'. |
sync_mode | boolean | If `True`, the media will be returned as a data URI and the output data won't be available in the request history. |
transparency_mode | string (enum) | The transparency mode to apply to the first and last frames. This controls how the transparent areas of the first and last frames are filled. |
return_frames_zip | boolean | If true, also return a ZIP file containing all generated frames. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
Pick a task: depth, pose, inpainting, outpainting or reframe, and add the inputs that task uses: a source video, a mask video or mask image, reference images, a first frame or a last frame. Wan VACE 14B renders at 480p, 580p or 720p, from 5 to 30 frames per second.
Advanced settings cover steps, guidance, sampler, shift, frame interpolation and temporal downsampling for longer sources. Each task also has its own card with only the inputs it needs.
Inspect mask boundaries through motion and ensure the edit does not alter areas you intended to preserve.