Model API'si

LTX-2.3 22B

LTX-2.3 22B ile video üret; ses ve görüntü yönlendirmesini ayrı ayarla.

Model kimliği

Her istekte bunu kullan
ltx-2.3-22b/text-to-video

Bu modelin kendi kimliği olan başka modları da var: ltx-2.3-22b/image-to-video.

Çalıştır

Girdiye ücret teklifi al, bu teklifle üretimi başlat, ardından işin durumunu sorgula. Önce RAYWAKE_API_KEY değişkenini ayarla; ayrıntılar için Kimlik doğrulama sayfasına bak.

# 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": "ltx-2.3-22b/text-to-video",
  "input": {
    "prompt": "A red ceramic cup on a wooden table, soft morning light"
  }
}'

# 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": "ltx-2.3-22b/text-to-video", "quote_id": "QUOTE_ID", "input": {"prompt":"A red ceramic cup on a wooden table, soft morning light"}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Girdi

ltx-2.3-22b/text-to-video girdi alanları
AlanTürAçıklama
promptzorunlustring
The prompt to generate the video from.
num_framesinteger
The number of frames to generate.

Varsayılan: 121

video_sizestring (enum)
The size of the generated video.

Varsayılan: landscape_16_9

Seçenekler: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

generate_audioboolean
Whether to generate audio for the video.

Varsayılan: true

use_multiscaleboolean
Whether to use multi-scale generation. If True, the model will generate the video at a smaller scale first, then use the smaller video to guide the generation of a video at or above your requested size. This results in better coherence and details.

Varsayılan: true

fpsnumber (enum)
The frames per second of the generated video.

Varsayılan: 24

Seçenekler: 24

num_inference_stepsinteger
The number of inference steps to use.

Varsayılan: 40

video_cfg_scalenumber
The Classifier-Free Guidance (CFG) scale for the video. Higher values result in more consistent and focused video content.

Varsayılan: 3

video_stg_scalenumber
The Spatiotemporal Guidance (STG) scale for the video. Higher values result in more consistent and focused video content.

Varsayılan: 0

video_rescaling_scalenumber
The rescaling scale for the video. Controls the ratio between classifier-free guidance and spatiotemporal guidance.

Varsayılan: 0.7

video_modality_scalenumber
The modality scale for the video. Controls the ratio between video and audio modalities.

Varsayılan: 3

audio_cfg_scalenumber
The Classifier-Free Guidance (CFG) scale for the audio. Higher values result in more consistent and focused audio content.

Varsayılan: 7

audio_stg_scalenumber
The Spatiotemporal Guidance (STG) scale for the audio. Higher values result in more consistent and focused audio content.

Varsayılan: 0

audio_rescaling_scalenumber
The rescaling scale for the audio. Controls the ratio between classifier-free guidance and spatiotemporal guidance.

Varsayılan: 0.7

audio_modality_scalenumber
The modality scale for the audio. Controls the ratio between video and audio modalities.

Varsayılan: 3

gradient_estimation_gammanumber
The gamma of gradient estimation during denoising. Set to 0 to disable.

Varsayılan: 2

use_restart_samplingboolean
Whether to use restart sampling. This will inject a small amount of noise during each denoising step, which can help improve the quality of the generated video.

Varsayılan: false

schedulerstring (enum)
The scheduler to use.

Varsayılan: ltx2

Seçenekler: ltx2, linear_quadratic, beta

accelerationstring (enum)
The acceleration level to use.

Varsayılan: regular

Seçenekler: none, regular, high, full

camera_lorastring (enum)
The camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.

Varsayılan: none

Seçenekler: none

camera_lora_scalenumber (enum)
The scale of the camera LoRA to use. This allows you to control the camera movement of the generated video more accurately than just prompting the model to move the camera.

Varsayılan: 1

Seçenekler: 1

negative_promptstring
The negative prompt to generate the video from.

Varsayılan: news broadcast, 3d animation, computer graphics, pc game, console game, video game, cartoon, childish, watermark, logo, text, on screen text, subtitles, titles, signature, slowmo, static

seedinteger
The seed for the random number generator.
enable_prompt_expansionboolean
Whether to enable prompt expansion.

Varsayılan: true

video_output_typestring (enum)
The output type of the generated video.

Varsayılan: X264 (.mp4)

Seçenekler: X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), GIF (.gif)

video_qualitystring (enum)
The quality of the generated video.

Varsayılan: high

Seçenekler: high

video_write_modestring (enum)
The write mode of the generated video.

Varsayılan: balanced

Seçenekler: fast, balanced, small

sync_modeboolean
If `True`, the media will be returned as a data URI and the output data won't be available in the request history.

Varsayılan: false

distill_lora_first_pass_scalenumber
The scale of the distill LoRA to use for the first pass. Set to 0 to disable.

Varsayılan: 0.2

distill_lora_second_pass_scalenumber
The scale of the distill LoRA to use for the second and subsequent passes.

Varsayılan: 0.5

Çıktı

Başarılı bir iş, sonuçlarını outputs altında listeler; dosyalar bizim tarafımızda saklanır. Tüm alanlar için İşler sayfasına bak.

İş yanıtından bir bölüm
"outputs": [
  { "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]

Fiyatlandırma

  • 1 megapixel$0,01/ megapiksel

Girdinin kesin ücreti ücret teklifinden gelir. Bakiye nasıl kesinleşir?