LTX2 Text2Video
LTX-2 is the first DiT-based audio-video foundation model that contains all core capabilities of modern video generation in one model: synchronized audio and video, high fidelity, multiple performance modes, production-ready outputs.
Query Parameters
Optional. Invocation mode. Defaults to synchronous.
"sync" | "async_websocket" | "async_callback"Required when mode=async_callback. Used to receive async results.
Optional. Defaults to false. When true, returns the points cost without executing the task.
Header Parameters
""Request Body
application/json
Your image description. Tell the AI what you want to see.
""What to avoid in the image. Describe what you don't want.
""The shape of your image.
"1:1""16:9" | "1:1" | "9:16"The number of images to generate.
5Response Body
application/json
curl -X POST "https://api.crowdcomputed.com/api/v1/generate/ltx2-text2video?mode=sync&callback=&costLookup=false" \ -H "token: " \ -H "Content-Type: application/json" \ -d '{ "prompt": "", "imageRatio": "1:1", "imageCount": 5 }'Text2Image Qwen2512 POST
Qwen-Image-2512 significantly reduces the “AI-generated” look and substantially enhances overall image realism, especially for human subjects; delivers notably more detailed rendering of landscapes, animal fur, and other natural elements; improves the accuracy and quality of textual elements, achieving better layout and more faithful multimodal (text + image) composition
Image Edit Qwen2511 POST
Qwen-Image-Edit-2511 is another enhanced iteration based on the previous version, bringing a better experience in terms of character consistency, multi-subject scene stability, editing style capabilities and spatial geometry understanding.