egaki 0.1.0 → 0.2.0
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/CHANGELOG.md +30 -0
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -2,6 +2,36 @@
|
|
|
2
2
|
|
|
3
3
|
All notable changes to this project will be documented in this file.
|
|
4
4
|
|
|
5
|
+
## 0.2.0
|
|
6
|
+
|
|
7
|
+
1. **New `egaki video` command** — generate videos from text prompts or still images.
|
|
8
|
+
Full support for all AI Gateway video providers:
|
|
9
|
+
|
|
10
|
+
```bash
|
|
11
|
+
egaki video "a paper boat drifting on a calm lake at sunrise" -o boat.mp4
|
|
12
|
+
egaki video "timelapse of a stormy sea" -m google/veo-3.1-generate-001 --duration 8 -o storm.mp4
|
|
13
|
+
egaki video "animate the clouds slowly" --input photo.jpg -m klingai/kling-v2.6-i2v -o animated.mp4
|
|
14
|
+
```
|
|
15
|
+
|
|
16
|
+
Supported models: Google Veo 3.0/3.1, Kling v2.5/v2.6/v3.0, Bytedance Seedance,
|
|
17
|
+
Alibaba Wan, xAI Grok video.
|
|
18
|
+
|
|
19
|
+
2. **Full video options** — `--duration`, `--resolution`, `--aspect-ratio`, `--fps`,
|
|
20
|
+
`--seed`, `--count`, `--input` (image-to-video), `--stdout`, `--json`.
|
|
21
|
+
|
|
22
|
+
3. **`egaki models --type` filter** — filter model listing by modality:
|
|
23
|
+
|
|
24
|
+
```bash
|
|
25
|
+
egaki models --type video
|
|
26
|
+
egaki models --type image
|
|
27
|
+
egaki models --type all # default
|
|
28
|
+
```
|
|
29
|
+
|
|
30
|
+
Video models show duration range, capabilities (t2v, i2v, r2v), and resolution tiers.
|
|
31
|
+
|
|
32
|
+
4. **Egaki subscription covers video** — all gateway video models work with your
|
|
33
|
+
`egaki_...` key; usage is billed per-second based on model, resolution, and duration.
|
|
34
|
+
|
|
5
35
|
## 0.1.0
|
|
6
36
|
|
|
7
37
|
1. **New `egaki video` command** — generate videos from text prompts using AI models
|