@hypit/hypit 0.1.1 → 0.1.3
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
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
<p align="center">
|
|
2
|
-
<img alt="Hypit" src="https://
|
|
2
|
+
<img alt="Hypit" src="https://storage.googleapis.com/hypit-public-assets/showcase/npm/2026-09-10/logo.svg" width="400" height="143">
|
|
3
3
|
</p>
|
|
4
4
|
|
|
5
5
|
<h3 align="center">Clone any viral video with AI agents</h3>
|
|
@@ -40,7 +40,7 @@ Hypit gives AI agents (Claude Code, Codex...) a language and system to create vi
|
|
|
40
40
|
|
|
41
41
|
**To be clear:** cloning a video is the fastest way in, not the only one. You can start from our templates, or just describe the video you want and your agent writes the workflow from scratch. Generation models are optional too: a workflow can compile captions, motion graphics and code-rendered visuals into a finished video without calling a single model, so a video can cost exactly $0.
|
|
42
42
|
|
|
43
|
-
|
|
44
44
|
|
|
45
45
|
<p align="center"><em>SVML source on the left, with the corresponding video rendered live on the right.</em></p>
|
|
46
46
|
|
|
@@ -105,7 +105,7 @@ Drop in a video and your agent clones the whole workflow — or describe what yo
|
|
|
105
105
|
|
|
106
106
|
Star us, and you will receive all release notifications from GitHub without any delay!
|
|
107
107
|
|
|
108
|
-
|
|
109
109
|
|
|
110
110
|
## How to Contribute
|
|
111
111
|
|
package/package.json
CHANGED
|
@@ -2,7 +2,8 @@
|
|
|
2
2
|
|
|
3
3
|
`phone-ugc-v1` is a data-only Text Template for assembling image prompts. Its
|
|
4
4
|
[source](kits/phone-ugc-v1.svs) emits a fixed iPhone-video capture paragraph, followed by the supplied
|
|
5
|
-
Text slots, with paragraph separators.
|
|
5
|
+
Text slots in `person` → `shot` → `setting` order, with paragraph separators.
|
|
6
|
+
Import it as `@hypit/gpt-image-kits/phone-ugc-v1`.
|
|
6
7
|
|
|
7
8
|
For creative direction, see the Image direction page in the Hypit Skill.
|
|
8
9
|
|
|
@@ -13,17 +14,20 @@ selecting or authoring another Text Template. The caller supplies the variable d
|
|
|
13
14
|
|
|
14
15
|
| Text slot | Required | Content |
|
|
15
16
|
| --- | --- | --- |
|
|
16
|
-
| `
|
|
17
|
-
| `
|
|
18
|
-
| `
|
|
17
|
+
| `person` | No | Person or cast, appearance and styling; identity references and what they preserve. |
|
|
18
|
+
| `shot` | Yes | Camera view, framing, posture, gaze, action and interaction with people or props. |
|
|
19
|
+
| `setting` | No | Surrounding place, palette, structures and objects; scene references and what they preserve. |
|
|
19
20
|
|
|
20
|
-
|
|
21
|
-
|
|
22
|
-
|
|
21
|
+
For a complete new character-and-scene image, supply all three as ordinary paragraphs. A derived
|
|
22
|
+
view may inherit its person or setting from connected references and omit those slots. Omitted
|
|
23
|
+
blocks add no empty paragraphs. State the necessary reference responsibilities in the slot they
|
|
24
|
+
affect. Each slot accepts an ordinary Text Output and can describe more than one person or relationship.
|
|
25
|
+
The template produces Text; the image Surface consumes it. Actual reference Resources and model
|
|
26
|
+
parameters are connected on that Surface.
|
|
23
27
|
|
|
24
28
|
## Assemble the prompt
|
|
25
29
|
|
|
26
|
-
Given authored Text Outputs `portrait-shot` and `portrait-
|
|
30
|
+
Given authored Text Outputs `portrait-person`, `portrait-shot` and `portrait-setting`, this fragment assembles the
|
|
27
31
|
prompt and passes it to `gpt:Image`:
|
|
28
32
|
|
|
29
33
|
```svml
|
|
@@ -32,13 +36,14 @@ prompt and passes it to `gpt:Image`:
|
|
|
32
36
|
<import as="ugc" source="@hypit/gpt-image-kits/phone-ugc-v1"/>
|
|
33
37
|
|
|
34
38
|
<text:Render id="portrait-prompt" template={ugc.phone-ugc-v1}>
|
|
39
|
+
<text:Set name="person" text={portrait-person}/>
|
|
35
40
|
<text:Set name="shot" text={portrait-shot}/>
|
|
36
|
-
<text:Set name="
|
|
41
|
+
<text:Set name="setting" text={portrait-setting}/>
|
|
37
42
|
</text:Render>
|
|
38
43
|
|
|
39
44
|
<gpt:Image id="portrait" prompt={portrait-prompt} aspect-ratio="9:16" resolution="2K"/>
|
|
40
45
|
```
|
|
41
46
|
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
47
|
+
Connect reference images through `gpt:Reference` children on `gpt:Image` in the order described by
|
|
48
|
+
the prompt. For example, a `person` paragraph can inherit identity from reference 1 while `shot`
|
|
49
|
+
describes holding the product from reference 2. The Text does not create Resource bindings.
|
|
@@ -8,27 +8,27 @@
|
|
|
8
8
|
text-template.phone-ugc-v1.block.capture {
|
|
9
9
|
kind: fixed;
|
|
10
10
|
order: 10;
|
|
11
|
-
text: "A photograph
|
|
11
|
+
text: "A photograph captured as a single frame from a video actually shot on an iPhone, with the texture of real iPhone footage. The image looks real, without an oily, overprocessed finish. The background is clearly visible, with no depth-of-field blur. Skin texture is natural and fine, and the lighting is natural. The image is coherent and free of visual artifacts.";
|
|
12
12
|
}
|
|
13
13
|
|
|
14
|
-
text-template.phone-ugc-v1.block.
|
|
14
|
+
text-template.phone-ugc-v1.block.person {
|
|
15
15
|
kind: slot;
|
|
16
16
|
order: 20;
|
|
17
|
-
slot:
|
|
18
|
-
optional:
|
|
17
|
+
slot: person;
|
|
18
|
+
optional: true;
|
|
19
19
|
}
|
|
20
20
|
|
|
21
|
-
text-template.phone-ugc-v1.block.
|
|
21
|
+
text-template.phone-ugc-v1.block.shot {
|
|
22
22
|
kind: slot;
|
|
23
23
|
order: 30;
|
|
24
|
-
slot:
|
|
24
|
+
slot: shot;
|
|
25
25
|
optional: false;
|
|
26
26
|
}
|
|
27
27
|
|
|
28
|
-
text-template.phone-ugc-v1.block.
|
|
28
|
+
text-template.phone-ugc-v1.block.setting {
|
|
29
29
|
kind: slot;
|
|
30
30
|
order: 40;
|
|
31
|
-
slot:
|
|
31
|
+
slot: setting;
|
|
32
32
|
optional: true;
|
|
33
33
|
}
|
|
34
34
|
</sheet>
|