@doufunao123/asset-gateway 0.6.0 → 0.7.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +30 -3
- package/dist/index.js +1390 -457
- package/package.json +3 -1
package/README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
|
2
2
|
|
|
3
3
|
Lightweight npm CLI client for the universal asset generation gateway.
|
|
4
4
|
|
|
5
|
+
The CLI is a thin wrapper around `@doufunao123/assetforge-sdk`. For programmatic access, use the SDK directly.
|
|
6
|
+
|
|
5
7
|
## Install
|
|
6
8
|
|
|
7
9
|
```bash
|
|
@@ -40,7 +42,7 @@ Config file format:
|
|
|
40
42
|
```json
|
|
41
43
|
{
|
|
42
44
|
"token": "agk_...",
|
|
43
|
-
"gateway_url": "https://
|
|
45
|
+
"gateway_url": "https://asset.origingame.dev"
|
|
44
46
|
}
|
|
45
47
|
```
|
|
46
48
|
|
|
@@ -56,10 +58,21 @@ asset-gateway auth clear # Remove saved credentials
|
|
|
56
58
|
asset-gateway generate image --prompt "a cat" --size 1024x1024
|
|
57
59
|
asset-gateway generate image --prompt "icon" --transparent --provider flux
|
|
58
60
|
asset-gateway generate video --prompt "ocean waves"
|
|
59
|
-
asset-gateway generate
|
|
60
|
-
asset-gateway generate
|
|
61
|
+
asset-gateway generate sfx --prompt "epic battle impact" --duration 3
|
|
62
|
+
asset-gateway generate tts --prompt "（开心）今天天气真好！" --voice 冰糖
|
|
63
|
+
asset-gateway voice design --voice-prompt "warm narrator" --preview-text "Welcome." --name narrator --output ./narrator.wav
|
|
64
|
+
asset-gateway voice clone --audio ./sample.wav --preview-text "Welcome back." --name clone --output ./clone.wav
|
|
65
|
+
asset-gateway generate character --prompt "medieval knight" --format fbx --pbr
|
|
66
|
+
asset-gateway generate prop --prompt "ornate treasure chest" --polycount 5000
|
|
67
|
+
asset-gateway generate model --image https://example.com/ref.png --ai-model latest
|
|
61
68
|
asset-gateway generate text --prompt "describe a forest" --model gpt-5.4
|
|
62
69
|
|
|
70
|
+
# 3D post-processing
|
|
71
|
+
asset-gateway process3d remesh --task-id <id> --format glb --polycount 20000
|
|
72
|
+
asset-gateway process3d retexture --task-id <id> --prompt "worn bronze armor"
|
|
73
|
+
asset-gateway process3d rig --task-id <id> --height 1.8
|
|
74
|
+
asset-gateway process3d refine --task-id <id> --pbr --hd-texture
|
|
75
|
+
|
|
63
76
|
# Providers
|
|
64
77
|
asset-gateway provider list
|
|
65
78
|
asset-gateway provider health
|
|
@@ -76,6 +89,20 @@ asset-gateway describe
|
|
|
76
89
|
asset-gateway describe generate
|
|
77
90
|
```
|
|
78
91
|
|
|
92
|
+
Programmatic TTS uses the SDK directly. MiMo voices include `冰糖`, `茉莉`, `苏打`, `白桦`, `Mia`, `Chloe`, `Milo`, and `Dean`; prompts may include audio tags such as `（开心）`, `(唱歌)`, or `[whisper]`.
|
|
93
|
+
|
|
94
|
+
```ts
|
|
95
|
+
await forge.tts("（开心）今天天气真好！", { voice: "冰糖" });
|
|
96
|
+
```
|
|
97
|
+
|
|
98
|
+
Voice design and clone are also available from the CLI:
|
|
99
|
+
|
|
100
|
+
```bash
|
|
101
|
+
asset-gateway voice design --voice-prompt "warm documentary narrator" --preview-text "Welcome to AssetForge." --name narrator --output ./narrator.wav
|
|
102
|
+
asset-gateway voice clone --audio ./sample.wav --preview-text "Welcome back." --name clone --output ./clone.wav
|
|
103
|
+
asset-gateway voice list --type vc
|
|
104
|
+
```
|
|
105
|
+
|
|
79
106
|
## Output
|
|
80
107
|
|
|
81
108
|
JSON by default. Use `--human` for readable output, `--fields` to filter:
|