@vibes.diy/prompts 14.3.353 → 14.3.354

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/llms/image-gen.md CHANGED
@@ -280,6 +280,8 @@ Your `access.js` governs your app's own records — the story, the hat, the roas
280
280
 
281
281
  Every `<ImgGen>` draws with the app's default image model. `listModels({ kind: "image" })` (from `call-ai`, beside `callAI`) returns the image models this app can use, the app's own choice first, and each entry's `id` goes straight into the `model` prop: `<ImgGen prompt="An astronaut riding a horse" model={m.id} />`. The entry with `isDefault: true` is the one ImgGen uses when `model` is left out; with `images` present the default is the platform's image-edit model instead, so img2img leaves `model` out (see above). When the app's maker saved their own provider key, it covers the image model they chose in settings; other models run on the person's credits. The callAI skill's "Choosing a model" section lists every field.
282
282
 
283
+ An app whose owner picks the image model (a Settings choice kept in the app's own database) also saves that `id` as `model` on each record it paints, beside `prompt`, and passes `model={record.model}` to that record's `<ImgGen>`; a picture Vibes paints into the record from a texted photo then uses the same model. Leave Prodia models out of a selfie app's choices, since they restyle without keeping a face.
284
+
283
285
  To compare image models, call `listModels({ kind: "image" })` and render one `<ImgGen>` per entry with `model={m.id}`. Every picture shares one prompt, each card is labelled with `m.name`, and each picture uses its stored audition record's `_id` so a reload shows the saved pictures. The lineup is on screen before any picture is: one card per model with its name and an empty frame, the prompt box and the draw button above them, so the first screen reads as a lineup waiting for its press; while the model list is still loading the cards show a `Skeleton`, and a list that fails to load leaves the frames in place with one sentence in the app's own words, never a banner over the page. Each click saves one new record per model, with its prompt and model choice:
284
286
 
285
287
  ### `App.jsx`
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@vibes.diy/prompts",
3
- "version": "14.3.353",
3
+ "version": "14.3.354",
4
4
  "type": "module",
5
5
  "main": "./index.js",
6
6
  "exports": {
@@ -39,10 +39,10 @@
39
39
  "license": "SEE LICENSE IN LICENSE.md",
40
40
  "dependencies": {
41
41
  "@adviser/cement": "~0.5.37",
42
- "@vibes.diy/api-types": "14.3.353",
43
- "@vibes.diy/call-ai-v2": "14.3.353",
44
- "@vibes.diy/identity": "14.3.353",
45
- "@vibes.diy/use-vibes-types": "14.3.353",
42
+ "@vibes.diy/api-types": "14.3.354",
43
+ "@vibes.diy/call-ai-v2": "14.3.354",
44
+ "@vibes.diy/identity": "14.3.354",
45
+ "@vibes.diy/use-vibes-types": "14.3.354",
46
46
  "arktype": "~2.2.9",
47
47
  "json-schema-faker": "~0.6.4"
48
48
  },