LTX 2 Fast: Text-to-Video AI with 4K Motion & Sound Sync
Generate instant video previews with LTX 2 Fast—optimized for speed, low latency, and fast text-to-video generation.
Table of contents
1. Get started
Use RunComfy's API to run ltx/ltx-2/fast/text-to-video. For accepted inputs and outputs, see the model's schema.
curl --request POST \
--url https://model-api.runcomfy.net/v1/models/ltx/ltx-2/fast/text-to-video \
--header "Content-Type: application/json" \
--header "Authorization: Bearer <token>" \
--data '{
"prompt": "A photorealistic portrait of a stylish young woman sitting at an outdoor Parisian café with red woven bistro chairs and circular white tables. She has long, smooth, straight, honey-blonde hair, parted neatly in the middle. She is wearing a classic black beret, a crisp white button-up shirt, and a dark blue tie with diagonal gold stripes. Over her shirt, she wears a slightly oversized black leather jacket. She accessorizes with pearl and gold hoop earrings on one ear. Her makeup features sharp, winged eyeliner, defined eyebrows, and a natural nude lip color, giving her a chic, confident look. The scene captures a soft afternoon ambient light, with clear reflections on the glass window behind her. Through the window, vintage-style golden lettering that reads \"ROYH...\" is visible, partially cut off due to her posture. In the background, a Parisian street is subtly mirrored in the glass. The camera angle is eye-level, front-facing and slightly to the right, creating a natural, elegant composition. The color palette is warm and clean with a touch of Parisian café ambience. Extremely detailed, 8k resolution, sharp focus, shallow depth of field, photorealistic style, natural lighting, cinematic atmosphere, high fashion editorial aesthetic."
}'2. Authentication
Set the YOUR_API_TOKEN environment variable with your API key (manage keys in your Profile) and include it on every request as a Bearer token via the Authorization header: Authorization: Bearer $YOUR_API_TOKEN.
3. API reference
Submit a request
Submit an asynchronous generation job and immediately receive a request_id plus URLs to check status, fetch results, and cancel.
curl --request POST \
--url https://model-api.runcomfy.net/v1/models/ltx/ltx-2/fast/text-to-video \
--header "Content-Type: application/json" \
--header "Authorization: Bearer <token>" \
--data '{
"prompt": "A photorealistic portrait of a stylish young woman sitting at an outdoor Parisian café with red woven bistro chairs and circular white tables. She has long, smooth, straight, honey-blonde hair, parted neatly in the middle. She is wearing a classic black beret, a crisp white button-up shirt, and a dark blue tie with diagonal gold stripes. Over her shirt, she wears a slightly oversized black leather jacket. She accessorizes with pearl and gold hoop earrings on one ear. Her makeup features sharp, winged eyeliner, defined eyebrows, and a natural nude lip color, giving her a chic, confident look. The scene captures a soft afternoon ambient light, with clear reflections on the glass window behind her. Through the window, vintage-style golden lettering that reads \"ROYH...\" is visible, partially cut off due to her posture. In the background, a Parisian street is subtly mirrored in the glass. The camera angle is eye-level, front-facing and slightly to the right, creating a natural, elegant composition. The color palette is warm and clean with a touch of Parisian café ambience. Extremely detailed, 8k resolution, sharp focus, shallow depth of field, photorealistic style, natural lighting, cinematic atmosphere, high fashion editorial aesthetic."
}'Monitor request status
Fetch the current state for a request_id ("in_queue", "in_progress", "completed", or "cancelled").
curl --request GET \
--url https://model-api.runcomfy.net/v1/requests/{request_id}/status \
--header "Authorization: Bearer <token>"Retrieve request results
Retrieve the final outputs and metadata for the given request_id; if the job is not complete, the response returns the current state so you can continue polling.
curl --request GET \
--url https://model-api.runcomfy.net/v1/requests/{request_id}/result \
--header "Authorization: Bearer <token>"Cancel a request
Cancel a queued job by request_id, in-progress jobs cannot be cancelled.
curl --request POST \
--url https://model-api.runcomfy.net/v1/requests/{request_id}/cancel \
--header "Authorization: Bearer <token>"4. File inputs
Hosted file (URL)
Provide a publicly reachable HTTPS URL. Ensure the host allows server‑side fetches (no login/cookies required) and isn't rate‑limited or blocking bots. Recommended limits: images ≤ 50 MB (~4K), videos ≤ 100 MB (~2–5 min @ 720p). Prefer stable or pre‑signed URLs for private assets.
5. Schema
Input schema
{
"type": "object",
"title": "Input",
"required": [
"prompt"
],
"properties": {
"prompt": {
"title": "Prompt",
"description": "The textual description used to generate the video.",
"type": "string",
"default": "A photorealistic portrait of a stylish young woman sitting at an outdoor Parisian café with red woven bistro chairs and circular white tables. She has long, smooth, straight, honey-blonde hair, parted neatly in the middle. She is wearing a classic black beret, a crisp white button-up shirt, and a dark blue tie with diagonal gold stripes. Over her shirt, she wears a slightly oversized black leather jacket. She accessorizes with pearl and gold hoop earrings on one ear. Her makeup features sharp, winged eyeliner, defined eyebrows, and a natural nude lip color, giving her a chic, confident look. The scene captures a soft afternoon ambient light, with clear reflections on the glass window behind her. Through the window, vintage-style golden lettering that reads \"ROYH...\" is visible, partially cut off due to her posture. In the background, a Parisian street is subtly mirrored in the glass. The camera angle is eye-level, front-facing and slightly to the right, creating a natural, elegant composition. The color palette is warm and clean with a touch of Parisian café ambience. Extremely detailed, 8k resolution, sharp focus, shallow depth of field, photorealistic style, natural lighting, cinematic atmosphere, high fashion editorial aesthetic."
},
"duration": {
"title": "Duration",
"description": "",
"type": "integer",
"enum": [
6,
8,
10,
12,
14,
16,
18,
20
],
"default": 6
},
"resolution": {
"title": "Resolution",
"description": "The resolution of the generated video.",
"type": "string",
"enum": [
"1080p",
"1440p",
"2160p"
],
"default": "1080p"
},
"aspect_ratio": {
"title": "Aspect Ratio (W:H)",
"description": "The aspect ratio of the generated video.",
"type": "string",
"enum": [
"16:9"
],
"default": "16:9"
},
"fps": {
"title": "Frames Per Second",
"description": "Frames per second of the generated video.",
"type": "integer",
"enum": [
25,
50
],
"default": 25
},
"generate_audio": {
"title": "Generate Audio",
"description": "Whether to generate audio for the generated video.",
"type": "boolean",
"default": true
}
}
}Output schema
{
"output": {
"type": "object",
"properties": {
"image": {
"type": "string",
"format": "uri",
"description": "single image URL"
},
"video": {
"type": "string",
"format": "uri",
"description": "single video URL"
},
"images": {
"type": "array",
"description": "multiple image URLs",
"items": { "type": "string", "format": "uri" }
},
"videos": {
"type": "array",
"description": "multiple video URLs",
"items": { "type": "string", "format": "uri" }
}
}
}
}RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.
