# UGC Real 1: a realistic AI UGC image model Updated 2 Nov 2026 ## Short answer UGC Real 1 is VidLab's own image model. It makes pictures that look like a person took them on a phone: natural skin, an ordinary room, slightly imperfect framing. It costs $0.03 per image at any shape, you send words only, and you pay only for images that are made. It runs on the same API key and balance as every other model, so it takes one request to try it. The model page is [UGC Real 1](/vidlab-api/models/ugc-real-1). ## What it makes These five pictures show the look UGC Real 1 is made for: a creator talking to the camera, a selfie in a car, someone holding a product, a podcast guest, a presenter at a desk. ![A woman with long dark hair blowing across her face stands in a park under a blue sky with clouds, speaking to the camera and holding a small grey fluffy microphone.](/api-platform/examples/ugc-real-1/ugc-real-1-1.webp) ![A woman with straight brown hair and a pearl necklace takes a selfie in the front seat of a car, a grey seat belt across her chest and trees outside the window.](/api-platform/examples/ugc-real-1/ugc-real-1-2.webp) ![A woman with long dark hair and a surprised smile holds a small white perfume box while being interviewed with a handheld microphone in front of a red velvet curtain.](/api-platform/examples/ugc-real-1/ugc-real-1-3.webp) ![A smiling woman with short curly hair, in a blue and yellow striped knit jumper, sits in a cream armchair in front of dark blue bookshelves with a large microphone in front of her.](/api-platform/examples/ugc-real-1/ugc-real-1-4.webp) ![A man with swept-back dark hair and a beard looks into the camera with a surprised face, three skincare bottles on the table in front of him and a framed print on the wall behind.](/api-platform/examples/ugc-real-1/ugc-real-1-5.webp) Most image models are tuned for polish. UGC Real 1 is tuned for the opposite: the unretouched look of a real phone photo, which is what makes a creator-style ad believable. Skin has texture, hair is a little messy, and the background is a lived-in place with real objects in it, not a studio. ## Price One flat price covers every shape, and the shape does not change it. | Option | Price per image | | - | - | | Any aspect ratio | $0.03 | A batch of 100 images costs $3.00. A call that fails, or that is blocked by the content filter, is not charged. To see the exact price of a request before you run it, `POST /v1/estimate` answers for free and needs no key. ## Write it short You do not need a long prompt. Before it draws, UGC Real 1 writes your words out into a detailed description of a phone photo: the framing and camera height, the pose and what each hand is doing, the hair, the skin, the clothes, the objects in the room and where the light comes from. A short prompt such as "a woman in her kitchen, talking to the camera" gives a full, specific picture, and a more specific prompt keeps more of what you said. - Say who is in the picture and where they are. The model fills in what you leave open. - Name the clothes, colours and objects you care about. It keeps them. - Do not count on it for writing in the picture. The model is made for people and everyday scenes. A prompt can be up to 2,000 characters. ## Shapes `9:16` is the default, because UGC lives on vertical screens. You can also ask for `16:9`, `1:1`, `4:3`, `3:4`, `2:3` or `3:2` with `aspect_ratio`. Every call makes one image at the model's best size, so there is no resolution or count to choose. ## Call it Estimate, then generate. The key comes from the environment. ```bash curl -s -X POST https://vidlab.ai/v1/estimate \ -H "Content-Type: application/json" \ -d '{"model":"ugc-real-1","input":{"prompt":"a woman in her kitchen, talking to the camera"}}' curl -s -X POST https://vidlab.ai/v1/generations \ -H "Authorization: Bearer $VIDLAB_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{"model":"ugc-real-1","input":{"prompt":"a woman in her kitchen, talking to the camera","aspect_ratio":"9:16"},"max_price_usd":0.03}' ``` The answer is a job. Poll `GET /v1/generations/{id}` until it succeeds, then download the picture from `outputs`. The output links are signed and last 6 hours, so copy the files you want to keep. The [quickstart](/vidlab-api/docs/quickstart) shows the polling loop in Node and Python, and the [model list](/vidlab-api/docs/model-list) has a short section on this model. ## When to use something else UGC Real 1 takes words only. It does not take reference pictures, so it cannot put a particular person or product into a picture. When you need to edit a photo, or keep a face or a bottle exactly as photographed, pick a model that takes images: [Nano Banana Pro](/vidlab-api/models/nano-banana-pro) takes up to 14 reference pictures, and the [Nano Banana Pro price guide](/blog/nano-banana-pro-api-pricing) shows what it costs. A common pattern is to make the person with UGC Real 1 and then bring a product into the frame with an editing model. ## FAQ ### How much does a UGC Real 1 image cost? $0.03 per image, at any aspect ratio. Failed or blocked images are not charged. ### Can I send a reference photo? No. UGC Real 1 takes a prompt and an aspect ratio only, and a request that sends `images` is refused with `400 invalid_input` before anything is reserved. Use an editing model for reference pictures. ### Who makes it? VidLab. It is our own model, not one we resell, so it is listed under VidLab on the [models page](/vidlab-api/models) and is the first image model there. ### How long should my prompt be? A few words are enough, and up to 2,000 characters are allowed. The model writes your words out into a detailed photo description, so a short prompt still gives a full picture. ### Can I call it from an AI assistant? Yes. See [how to use VidLab models from Claude, Cursor or Codex](/blog/vidlab-mcp-claude-cursor-codex).