Loading API documentation
Generate an image from a text prompt using NVIDIA Cosmos3-Super via vLLM-Omni.
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientThe @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.
Set FAL_KEY as an environment variable in your runtime.
export FAL_KEY="YOUR_API_KEY"The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("nvidia/cosmos-3-super/text-to-image", {
input: {
prompt: "A photorealistic close-up of two damp hands shaping a spinning cylinder of wet gray clay on a pottery wheel, fingers pinching the walls upward into a narrow-necked vase, water glistening on the clay, soft studio lighting, shallow depth of field."
},
logs: true,
onQueueUpdate: (update) => {
if (update.status === "IN_PROGRESS") {
update.logs.map((log) => log.message).forEach(console.log);
}
},
});
console.log(result.data);
console.log(result.requestId);The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_KEY"
});When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.
The client API provides a convenient way to submit requests to the model.
import { fal } from "@fal-ai/client";
const { request_id } = await fal.queue.submit("nvidia/cosmos-3-super/text-to-image", {
input: {
prompt: "A photorealistic close-up of two damp hands shaping a spinning cylinder of wet gray clay on a pottery wheel, fingers pinching the walls upward into a narrow-necked vase, water glistening on the clay, soft studio lighting, shallow depth of field."
},
webhookUrl: "https://optional.webhook.url/for/results",
});You can fetch the status of a request to check if it is completed or still in progress.
import { fal } from "@fal-ai/client";
const status = await fal.queue.status("nvidia/cosmos-3-super/text-to-image", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
logs: true,
});Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.
import { fal } from "@fal-ai/client";
const result = await fal.queue.result("nvidia/cosmos-3-super/text-to-image", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.
You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.
You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.
We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.
import { fal } from "@fal-ai/client";
const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).
Read more about file handling in our file upload guide.
prompt string* requiredText prompt describing the image to generate.
negative_prompt stringContent to steer the generation away from (colors, objects, artifacts). Default value: ""
enable_prompt_expansion booleanExpand the prompt with OpenRouter before image generation. When enabled, the prompt is rewritten into the dense structured-JSON format Cosmos3 was trained on; generation falls back to the raw prompt if expansion fails.
enable_agentic_generation booleanAutomatically generate and compare multiple candidate images, then refine the prompt between rounds to better match the original request. This can improve prompt adherence but increases latency and billable image generations.
agentic_max_iterations integerMaximum number of refinement rounds when agentic generation is enabled. Default value: 2
agentic_samples_per_iteration integerCandidate images to generate and judge per agentic iteration. The best candidate advances to the next rewrite stage. Default value: 2
agentic_early_stop booleanStop early when a candidate image is already a strong match for the prompt. Default value: true
The size of the generated image. Each edge is clamped to 512-1280px (multiples of 16). Default value: square_hd
Possible enum values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9
Note: For custom image sizes, you can pass the width and height as an object:
"image_size": {
"width": 1280,
"height": 720
}num_inference_steps integerNumber of denoising steps. More steps yield higher quality but take longer. Default value: 28
guidance_scale floatClassifier-free guidance scale. Higher values increase prompt adherence at the cost of diversity. Default value: 4
num_images integerThe number of images to generate. Default value: 1
seed integerThe same seed and prompt given to the same model version will produce the same image every time.
enable_safety_checker booleanEnable content moderation for the input prompt and generated images. Disabling it requires account authorization; unauthorized requests are always checked, and images flagged as unsafe are returned as black images. Default value: true
sync_mode booleanIf True, the image is returned as a data URI and the output data won't be available in the request history.
output_format OutputFormatEnumThe format of the generated image. Default value: "jpeg"
Possible enum values: jpeg, png
{
"prompt": "A photorealistic close-up of two damp hands shaping a spinning cylinder of wet gray clay on a pottery wheel, fingers pinching the walls upward into a narrow-necked vase, water glistening on the clay, soft studio lighting, shallow depth of field.",
"negative_prompt": "",
"agentic_max_iterations": 2,
"agentic_samples_per_iteration": 2,
"agentic_early_stop": true,
"image_size": {
"height": 1024,
"width": 1024
},
"num_inference_steps": 28,
"guidance_scale": 4,
"num_images": 1,
"enable_safety_checker": true,
"output_format": "jpeg"
}The generated images.
seed integer* requiredThe seed used for generation.
Whether each generated image was flagged by the safety checker.
{
"images": [
{
"file_name": "cosmos3-vllm-example.jpeg",
"content_type": "image/jpeg",
"url": "https://v3b.fal.media/files/b/0a8fc99c/cosmos3-vllm-example.jpeg"
}
],
"seed": 1143,
"has_nsfw_concepts": [
false
]
}url string* requiredThe URL where the file can be downloaded from.
content_type stringThe mime type of the file.
file_name stringThe name of the file. It will be auto-generated if not provided.
file_size integerThe size of the file in bytes.
width integerThe width of the image
height integerThe height of the image
width integerThe width of the generated image. Default value: 512
height integerThe height of the generated image. Default value: 512