csviverdeia/food-analyzer

Análise nutricional de imagens de comida (calorias, macros, ingredientes) usando Qwen3-VL-2B + LoRA Ateeqq/food-analysis

Public

3 runs

Playground API Examples README Versions

Run csviverdeia/food-analyzer with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
image	string		Foto de comida (jpg/png). Pode ser de qualquer ângulo / contexto.
prompt	string		(Opcional) prompt customizado. Se vazio, usa o prompt padrão que pede JSON estruturado.
max_new_tokens	integer	512 Min: 128 Max: 2048	Máximo de tokens gerados (mais = JSON mais detalhado).
temperature	number	0 Max: 2	0.0 = determinístico (greedy). >0 = sampling. Pra JSON estruturado, use 0.0.
parse_json	boolean	True	Se true, tenta fazer parse do JSON antes de retornar (output vira dict).

{
  "type": "object",
  "title": "Input",
  "required": [
    "image"
  ],
  "properties": {
    "image": {
      "type": "string",
      "title": "Image",
      "format": "uri",
      "x-order": 0,
      "description": "Foto de comida (jpg/png). Pode ser de qualquer \u00e2ngulo / contexto."
    },
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "default": "",
      "x-order": 1,
      "description": "(Opcional) prompt customizado. Se vazio, usa o prompt padr\u00e3o que pede JSON estruturado."
    },
    "parse_json": {
      "type": "boolean",
      "title": "Parse Json",
      "default": true,
      "x-order": 4,
      "description": "Se true, tenta fazer parse do JSON antes de retornar (output vira dict)."
    },
    "temperature": {
      "type": "number",
      "title": "Temperature",
      "default": 0,
      "maximum": 2,
      "minimum": 0,
      "x-order": 3,
      "description": "0.0 = determin\u00edstico (greedy). >0 = sampling. Pra JSON estruturado, use 0.0."
    },
    "max_new_tokens": {
      "type": "integer",
      "title": "Max New Tokens",
      "default": 512,
      "maximum": 2048,
      "minimum": 128,
      "x-order": 2,
      "description": "M\u00e1ximo de tokens gerados (mais = JSON mais detalhado)."
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "object",
  "title": "Output"
}