sn-image-base

1# sn-image-base
2 
3## Dependency Installation
4 
5```bash
6pip install -r requirements.txt
7```
8 
9## Overview
10 
11`sn-image-base` is the base-layer skill (tier 0) of the SenseNova-Skills project and provides four low-level tools:
12 
13- `sn-image-generate`: image generation (calls text-to-image-no-enhance API)
14- `sn-image-edit`: image editing with SenseNova U1.5 Lite (calls `/images/edits`)
15- `sn-image-recognize`: image recognition (uses VLM to analyze image content)
16- `sn-text-optimize`: text optimization (uses LLM to process text)
17 
18This skill **does not perform any input preprocessing** and only calls backend services to return results.
19 
20## Tools List
21 
22### sn-image-generate
23 
24Image generation tool that calls the text-to-image-no-enhance API.
25 
26`--prompt` is required; all other parameters are optional:
27 
28| Parameter | Type | Default | Description |
29|------|------|--------|------|
30| `--prompt` | string | **Required** | Prompt text for image generation |
31| `--negative-prompt` | string | `""` | Negative prompt |
32| `--image-size` | string | `2k` | Image size preset (case-insensitive). Recommended: `2k`. `4k` is supported by `sensenova-u1.5-lite`; other SenseNova image models may reject it. Other values → `status=failed`. |
33| `--aspect-ratio` | string | `16:9` | Aspect ratio, e.g. `1:1`, `16:9`, `9:16` |
34| `--seed` | int | `None` | Random seed for reproducible generation |
35| `--unet-name` | string | `None` | Specify a UNet model name |
36…