@hypit/hypit 0.2.8 → 0.2.10

package/README.md

@@ -209,6 +209,12 @@ commands and the repository layout.
     </td>
     <td><a href="https://api.pollo.ai/?utm_source=hypit">Pollo API</a> gives developers access to 300+ AI image and video models through a single API, with competitive rates. One API key connects you to multiple model providers and scales from 10 to 10,000+ requests.</td>
   </tr>
+  <tr>
+    <td width="220" align="center">
+      <a href="https://beatapi.io"><img alt="BeatAPI" src="./docs/public/beatapi.png" width="165"></a>
+    </td>
+    <td><a href="https://beatapi.io">BeatAPI</a> is the professional capability layer for any agent. We provide AI models, real-world data, task-ready capabilities, and professional workspaces that help agents complete real-world tasks.</td>
+  </tr>
 </table>
 
 ## ⭐ Star History

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@hypit/hypit",
-  "version": "0.2.8",
+  "version": "0.2.10",
   "homepage": "https://hypit.ai",
   "repository": {
     "type": "git",
@@ -236,8 +236,9 @@
     "@hypit/program-space": "workspace:*",
     "@hypit/project-context-node": "workspace:*",
     "@hypit/protocol": "workspace:*",
-    "@hypit/provider-hyperframes-local": "workspace:*",
+    "@hypit/provider-beatapi": "workspace:*",
     "@hypit/provider-hiapi": "workspace:*",
+    "@hypit/provider-hyperframes-local": "workspace:*",
     "@hypit/provider-hypihub": "workspace:*",
     "@hypit/provider-image-opencv-local": "workspace:*",
     "@hypit/provider-media-local": "workspace:*",

package/packages/media-execution/src/execute.ts

@@ -802,6 +802,7 @@ export async function executeRenderStillVideo(
       "select=eq(n\\,0)",
       "loop=loop=-1:size=1:start=0",
       `trim=start_frame=0:end_frame=${frames}`,
+      `settb=expr=${denominator}/${numerator}`,
       `setpts=N*${denominator}/(${numerator}*TB)`,
     ].join(",");
     let argv: string[];
@@ -1278,7 +1279,6 @@ export async function executeMuxProgramMedia(
         "-y", "-i", visualPath, "-i", audioPath,
         "-map", `0:${visual.index}`, "-map", "1:0",
         "-c:v", "copy", "-c:a", "aac", "-ar", "48000", "-ac", "2",
-        "-frames:v", String(need.visual.frameCount),
         "-movflags", "+faststart", output,
       ],
       timeoutMs: env.processTimeoutMs,

package/packages/pixverse/README.md

@@ -1,16 +1,18 @@
 # `@hypit/pixverse`
 
-Exact author/compute contracts and a package-owned author Surface for PixVerse V6.
+Exact author/compute contracts and package-owned author Surfaces for PixVerse. The package carries
+two exact models, `pixverse-v6` and `pixverse-c1`, and selects no Provider, API key or network
+execution. The selected Provider implements the exact capability.
 
-The Surface projects the primary result to an ordinary video Artifact. The package contains no
-Provider selection, API key or network execution. The selected Provider implements its exact
-capability.
-
-Connect prompt and frames as ordinary graph edges:
+Both models render 1 to 15 seconds at `360p`, `540p`, `720p` or `1080p` from a prompt of up to
+5,000 characters. `<pix:Video>` generates from the prompt, from a first frame, or from a first and
+last frame; `<pix:ReferenceVideo>` generates from the image and video subjects its `Reference`
+children carry.
 
 ```xml
 <pix:Video
   id="opening"
+  model="v6"
   prompt={line}
   duration="5"
   quality="720p"
@@ -18,17 +20,24 @@ Connect prompt and frames as ordinary graph edges:
   generate-audio="true"
 />
 
-<pix:Video id="bridge" prompt={motion} duration="5" quality="720p"
+<pix:Video id="bridge" model="c1" prompt={motion} duration="5" quality="720p"
   first-frame={hero.image} last-frame={product.image}/>
+
+<pix:ReferenceVideo id="fusion" model="v6" prompt={outfit} duration="5" quality="720p" aspect-ratio="16:9">
+  <pix:Reference image={character.image}/>
+  <pix:Reference image={clothes.image}/>
+</pix:ReferenceVideo>
 ```
 
-The Surface only lowers this syntax into the package's exact model request. It does not select a
-Provider.
+The prompt addresses the references in the order they appear, as `@ref_1`, `@ref_2` and so on. V6
+takes up to ten image references and C1 up to seven. V6 also takes up to two video references
+totalling 15 seconds; those carry the length of the run, so that element states no `duration`, and
+`aspect-ratio="auto"` takes their shape.
 
-The model renders 1 to 15 seconds at `360p`, `540p`, `720p` or `1080p`. A prompt-only run states its
-`aspect-ratio`; a run that starts from a `first-frame` takes that frame's shape instead. A
-`last-frame` bridges from the first frame into one continuous shot, so it is not combined with
-`multi-clip`, which renders the prompt as several cuts.
+A prompt-only run states its `aspect-ratio`; a run that starts from a `first-frame` takes that
+frame's shape instead. A `last-frame` bridges from the first frame into one continuous shot, as do
+subject references, so neither is combined with V6's `multi-clip`, which renders the prompt as
+several cuts. `seed` and `multi-clip` are V6's own switches.
 
 `generate-audio` renders an audio track alongside the picture, including speech the prompt asks a
 character to say. The model exposes no separate voice, language or dialogue field, so a spoken line

package/packages/pixverse/src/activation.ts

@@ -2,10 +2,12 @@ import { createMarkupSurfaceHostFacet } from "@hypit/markup";
 import {
   pixverseComponent, pixverseDefinition, pixverseManifest, pixverseModuleRef, pixverseMarkupSurfaces,
 } from "./index.js";
-import { decodePixverseVideoSurface } from "./surface.js";
+import { decodePixverseReferenceVideoSurface, decodePixverseVideoSurface } from "./surface.js";
 export const hypitPackage = { format: "hypit.node-package@1" as const, modules: [{ manifest: pixverseManifest }], components: [pixverseComponent], hostFacets: [
   pixverseDefinition.hostFacet,
   createMarkupSurfaceHostFacet({ module: pixverseModuleRef,
     declaration: pixverseMarkupSurfaces.find((item) => item.name === "video")!, handler: decodePixverseVideoSurface }),
+  createMarkupSurfaceHostFacet({ module: pixverseModuleRef,
+    declaration: pixverseMarkupSurfaces.find((item) => item.name === "reference-video")!, handler: decodePixverseReferenceVideoSurface }),
 ] };
 export default hypitPackage;

package/packages/pixverse/src/index.ts

@@ -1,117 +1,231 @@
 import { artifactTypes } from "@hypit/artifact";
 import { sealGenerationPortRequest, sealGenerationPortTable } from "@hypit/generation";
-import type { GenerationPortTable, GenerationPortValue, GenerationRequest } from "@hypit/generation";
-import type { SurfaceAttributeVocabulary } from "@hypit/markup";
+import type {
+  GenerationPort,
+  GenerationPortRequirement,
+  GenerationPortTable,
+  GenerationPortValue,
+  GenerationRequest,
+} from "@hypit/generation";
+import type { SurfaceAttributeVocabulary, SurfacePortVocabulary } from "@hypit/markup";
 import { defineExactModelModule } from "@hypit/model-kit";
 import { textTypes } from "@hypit/text";
 
+import { pixverseRequestValidator } from "./validation.js";
+
 export const pixverseModuleRef = { name: "@hypit/pixverse", version: "1" } as const;
-export const pixverseModels = ["pixverse-v6"] as const;
+export const pixverseModels = ["pixverse-v6", "pixverse-c1"] as const;
 export type PixverseModel = typeof pixverseModels[number];
 
 const PIXVERSE_QUALITIES = ["360p", "540p", "720p", "1080p"] as const;
 const PIXVERSE_ASPECT_RATIOS = ["16:9", "4:3", "1:1", "3:4", "9:16", "2:3", "3:2", "21:9"] as const;
+/** V6 reads `auto` as the shape of the reference videos it generates from. */
+const PIXVERSE_V6_ASPECT_RATIOS = [...PIXVERSE_ASPECT_RATIOS, "auto"] as const;
 
-export const pixverseV6Ports: GenerationPortTable = sealGenerationPortTable({
-  model: "pixverse-v6",
-  result: "video",
-  ports: [
-    { name: "prompt", value: { kind: "text", maxChars: 5_000 }, minItems: 1, maxItems: 1 },
-    { name: "firstFrame", value: { kind: "media", accepts: ["image"] }, minItems: 0, maxItems: 1 },
-    { name: "lastFrame", value: { kind: "media", accepts: ["image"] }, minItems: 0, maxItems: 1 },
-    { name: "duration", value: { kind: "number", integer: true, minimum: 1, maximum: 15 }, minItems: 1, maxItems: 1 },
-    { name: "quality", value: { kind: "enum", values: [...PIXVERSE_QUALITIES] }, minItems: 1, maxItems: 1 },
-    { name: "aspectRatio", value: { kind: "enum", values: [...PIXVERSE_ASPECT_RATIOS] }, minItems: 0, maxItems: 1 },
-    { name: "generateAudio", value: { kind: "boolean" }, minItems: 0, maxItems: 1 },
-    { name: "multiClip", value: { kind: "boolean" }, minItems: 0, maxItems: 1 },
-    { name: "seed", value: { kind: "number", integer: true, minimum: 0, maximum: 2_147_483_647 }, minItems: 0, maxItems: 1 },
-  ],
-  requires: [
-    // A last frame states where a run that already has a first frame ends.
-    { kind: "requiresPresent", port: "lastFrame", needs: ["firstFrame"] },
-    // A run that starts from a frame inherits that frame's shape, and one that
-    // bridges two frames renders a single continuous shot.
-    { kind: "atMostOneOf", ports: ["aspectRatio", "firstFrame"] },
-    { kind: "atMostOneOf", ports: ["multiClip", "lastFrame"] },
-  ],
-});
+/**
+ * Exact PixVerse model inputs. V6 takes up to ten reference images and up to two reference videos,
+ * and carries the sampling seed and multi-clip switch its endpoints declare. C1 takes up to seven
+ * reference images and generates from a prompt, a frame or a pair of frames.
+ */
+function pixversePortTable(model: PixverseModel): GenerationPortTable {
+  const v6 = model === "pixverse-v6";
+  const referenceVideo: readonly GenerationPort[] = v6
+    ? [{ name: "referenceVideo", value: { kind: "media", accepts: ["video"] }, minItems: 0, maxItems: 2 }]
+    : [];
+  const v6Switches: readonly GenerationPort[] = v6
+    ? [
+        { name: "multiClip", value: { kind: "boolean" }, minItems: 0, maxItems: 1 },
+        { name: "seed", value: { kind: "number", integer: true, minimum: 0, maximum: 2_147_483_647 }, minItems: 0, maxItems: 1 },
+      ]
+    : [];
+  const v6Requires: readonly GenerationPortRequirement[] = v6
+    ? [
+        // A run that bridges two frames, and one that carries subject references, is a single
+        // continuous shot rather than several cuts.
+        { kind: "atMostOneOf", ports: ["multiClip", "lastFrame"] },
+        { kind: "atMostOneOf", ports: ["multiClip", "referenceImage"] },
+        // The reference videos carry the length of the generated run.
+        { kind: "atMostOneOf", ports: ["duration", "referenceVideo"] },
+      ]
+    : [];
+  return sealGenerationPortTable({
+    model,
+    result: "video",
+    ports: [
+      { name: "prompt", value: { kind: "text", maxChars: 5_000 }, minItems: 1, maxItems: 1 },
+      { name: "firstFrame", value: { kind: "media", accepts: ["image"] }, minItems: 0, maxItems: 1 },
+      { name: "lastFrame", value: { kind: "media", accepts: ["image"] }, minItems: 0, maxItems: 1 },
+      { name: "referenceImage", value: { kind: "media", accepts: ["image"] }, minItems: 0, maxItems: v6 ? 10 : 7 },
+      ...referenceVideo,
+      // Required except in the reference-video mode, which pixverseRequestValidator states.
+      { name: "duration", value: { kind: "number", integer: true, minimum: 1, maximum: 15 }, minItems: 0, maxItems: 1 },
+      { name: "quality", value: { kind: "enum", values: [...PIXVERSE_QUALITIES] }, minItems: 1, maxItems: 1 },
+      {
+        name: "aspectRatio",
+        value: { kind: "enum", values: v6 ? [...PIXVERSE_V6_ASPECT_RATIOS] : [...PIXVERSE_ASPECT_RATIOS] },
+        minItems: 0,
+        maxItems: 1,
+      },
+      { name: "generateAudio", value: { kind: "boolean" }, minItems: 0, maxItems: 1 },
+      ...v6Switches,
+    ],
+    requires: [
+      // A last frame states where a run that already has a first frame ends.
+      { kind: "requiresPresent", port: "lastFrame", needs: ["firstFrame"] },
+      // A run that starts from a frame inherits that frame's shape.
+      { kind: "atMostOneOf", ports: ["aspectRatio", "firstFrame"] },
+      // Frames and subject references are separate ways of placing an image in the run.
+      { kind: "atMostOneOf", ports: ["referenceImage", "firstFrame"] },
+      ...v6Requires,
+    ],
+  });
+}
 
 export const pixversePorts: Readonly<Record<PixverseModel, GenerationPortTable>> = {
-  "pixverse-v6": pixverseV6Ports,
+  "pixverse-v6": pixversePortTable("pixverse-v6"),
+  "pixverse-c1": pixversePortTable("pixverse-c1"),
 };
 
 export function sealPixverseRequest(
+  model: PixverseModel,
   ports: Readonly<Record<string, readonly GenerationPortValue[]>>,
 ): GenerationRequest {
-  return sealGenerationPortRequest(pixverseV6Ports, ports);
+  return sealGenerationPortRequest(pixversePorts[model], ports);
 }
 
 const pixverseBaseDefinition = defineExactModelModule({
   module: pixverseModuleRef,
-  endpoints: [{
-    key: "video",
-    requestTypeName: "PixverseV6Request",
-    producerName: "request-pixverse-v6",
-    ports: pixverseV6Ports,
-  }],
+  endpoints: ([["v6", "pixverse-v6"], ["c1", "pixverse-c1"]] as const).map(([key, model]) => ({
+    key,
+    requestTypeName: model === "pixverse-v6" ? "PixverseV6Request" : "PixverseC1Request",
+    producerName: `request-${model}`,
+    ports: pixversePorts[model],
+    validateRequest: pixverseRequestValidator(model),
+  })),
 });
 
 export const pixverseEndpoints = pixverseBaseDefinition.endpoints;
+export const pixverseEndpointsByModel = {
+  "pixverse-v6": pixverseEndpoints.v6!,
+  "pixverse-c1": pixverseEndpoints.c1!,
+} as const;
 export const pixverseComponent = pixverseBaseDefinition.component;
-const endpoint = pixverseEndpoints.video!;
 
-const pixverseAttributes: readonly SurfaceAttributeVocabulary[] = [
+const surfaceOutputs = Object.values(pixverseEndpoints).flatMap((endpoint) => [
+  endpoint.draftType,
+  ...Object.values(endpoint.mediaBindings).map((binding) => binding.type),
+]);
+
+const pixverseCommonAttributes: readonly SurfaceAttributeVocabulary[] = [
   { name: "id", kind: "identifier", required: true,
     summary: "Names this generation so its video Artifact can be referenced elsewhere in the Source." },
+  { name: "model", kind: "literal", required: true, values: ["v6", "pixverse-v6", "c1", "pixverse-c1"],
+    summary: "Chooses the exact PixVerse model that renders the video." },
   { name: "prompt", kind: "reference", required: true, accepts: [textTypes.text],
     summary: "The Text edge describing the shot, including any spoken line the model should voice." },
-  { name: "first-frame", kind: "reference", required: false, accepts: [artifactTypes.blob],
-    summary: "Starts the video from one image Artifact." },
-  { name: "last-frame", kind: "reference", required: false, accepts: [artifactTypes.blob],
-    summary: "Ends the video on one image Artifact, bridging from the first frame." },
-  { name: "duration", kind: "literal", required: true,
-    summary: "How many seconds of video to render, from 1 to 15." },
   { name: "quality", kind: "literal", required: true, values: [...PIXVERSE_QUALITIES],
     summary: "The size band the model renders at." },
-  { name: "aspect-ratio", kind: "literal", required: false, values: [...PIXVERSE_ASPECT_RATIOS],
-    summary: "The Frame shape of the generated video." },
   { name: "generate-audio", kind: "literal", required: false, values: ["true", "false"],
     summary: "Renders an audio track alongside the picture." },
-  { name: "multi-clip", kind: "literal", required: false, values: ["true", "false"],
-    summary: "Renders the prompt as several cuts instead of one continuous shot." },
   { name: "seed", kind: "literal", required: false,
-    summary: "Seeds the model's sampling so a rerun stays close to this one." },
+    summary: "Seeds V6's sampling so a rerun stays close to this one." },
 ];
 
-export const pixverseMarkupSurfaces = [{
+const pixverseAspectRatio: SurfaceAttributeVocabulary = {
+  name: "aspect-ratio", kind: "literal", required: false, values: [...PIXVERSE_V6_ASPECT_RATIOS],
+  summary: "The Frame shape of the generated video.",
+};
+
+const pixverseVideoPort: readonly SurfacePortVocabulary[] = [{
   name: "video",
-  tag: "Video",
-  mode: "structured" as const,
-  outputs: [endpoint.draftType, endpoint.mediaBindings.firstFrame!.type, endpoint.mediaBindings.lastFrame!.type],
-  vocabulary: {
-      summary: "Generates one video with the exact PixVerse V6 model from a Text prompt, optionally starting from a frame or bridging two.",
-    attributes: pixverseAttributes,
-    ports: [{
-      name: "video",
-      type: artifactTypes.blob,
-      summary: "The generated video, addressed as `<id>.video`.",
-    }],
-    example: `<pix:Video
+  type: artifactTypes.blob,
+  summary: "The generated video, addressed as `<id>.video`.",
+}];
+
+const pixverseQualityNote = "`quality` is `360p`, `540p`, `720p` or `1080p`, and `duration` is 1 to 15 seconds.";
+const pixversePromptNote = "A spoken line belongs in the prompt; the model exposes no separate voice, language or dialogue field.";
+const pixverseModelNote = "V6 accepts `seed` and up to ten references; C1 accepts up to seven references.";
+
+export const pixverseMarkupSurfaces = [
+  {
+    name: "video",
+    tag: "Video",
+    mode: "structured" as const,
+    outputs: surfaceOutputs,
+    vocabulary: {
+      summary: "Generates one video with an exact PixVerse model from a Text prompt, optionally starting from a frame or bridging two.",
+      attributes: [
+        ...pixverseCommonAttributes,
+        { name: "duration", kind: "literal" as const, required: true,
+          summary: "How many seconds of video to render, from 1 to 15." },
+        { name: "first-frame", kind: "reference" as const, required: false, accepts: [artifactTypes.blob],
+          summary: "Starts the video from one image Artifact." },
+        { name: "last-frame", kind: "reference" as const, required: false, accepts: [artifactTypes.blob],
+          summary: "Ends the video on one image Artifact, bridging from the first frame." },
+        pixverseAspectRatio,
+        { name: "multi-clip", kind: "literal" as const, required: false, values: ["true", "false"],
+          summary: "Renders the prompt as several cuts instead of one continuous shot, on V6." },
+      ],
+      ports: pixverseVideoPort,
+      example: `<pix:Video
   id="opening"
+  model="v6"
   prompt={line}
   duration="5"
   quality="720p"
   aspect-ratio="9:16"
   generate-audio="true"
 />`,
-    notes: [
-      "A run that starts from a frame takes its shape from that frame, so `aspect-ratio` states the shape only for a prompt-only run.",
-      "A `last-frame` bridges from the `first-frame` into one continuous shot, so it is not combined with `multi-clip`.",
-      "A spoken line belongs in the prompt; the model exposes no separate voice, language or dialogue field.",
-      "The Surface lowers the element into the package's exact model request and selects no Provider.",
-    ],
+      notes: [
+        pixverseQualityNote,
+        pixverseModelNote,
+        "A run that starts from a frame takes its shape from that frame, so `aspect-ratio` states the shape only for a prompt-only run.",
+        "A `last-frame` bridges from the `first-frame` into one continuous shot, so it is not combined with `multi-clip`.",
+        pixversePromptNote,
+        "The element accepts no children and no text content.",
+      ],
+    },
+  },
+  {
+    name: "reference-video",
+    tag: "ReferenceVideo",
+    mode: "structured" as const,
+    outputs: surfaceOutputs,
+    vocabulary: {
+      summary: "Generates one video with an exact PixVerse model from a Text prompt and the image or video subjects it carries.",
+      attributes: [
+        ...pixverseCommonAttributes,
+        { name: "duration", kind: "literal" as const, required: false,
+          summary: "How many seconds of video to render, from 1 to 15; video references carry their own length." },
+        pixverseAspectRatio,
+      ],
+      children: [{
+        tag: "Reference",
+        cardinality: "many" as const,
+        summary: "Attaches one subject Artifact the model generates from, chosen by an `image` or `video` reference.",
+        attributes: [
+          { name: "image", kind: "reference" as const, required: false, accepts: [artifactTypes.blob],
+            summary: "Selects the image Artifact whose subject the generated video carries." },
+          { name: "video", kind: "reference" as const, required: false, accepts: [artifactTypes.blob],
+            summary: "Selects the video Artifact whose motion and subject the generated video carries." },
+        ],
+      }],
+      ports: pixverseVideoPort,
+      example: `<pix:ReferenceVideo id="fusion" model="v6" prompt={outfit} duration="5" quality="720p" aspect-ratio="16:9">
+  <pix:Reference image={character.image}/>
+  <pix:Reference image={clothes.image}/>
+</pix:ReferenceVideo>`,
+      notes: [
+        pixverseQualityNote,
+        pixverseModelNote,
+        "The prompt addresses the references in order as `@ref_1`, `@ref_2` and so on.",
+        "`Reference` carries exactly one of `image` or `video`, and is empty.",
+        "V6 accepts up to two video references totalling 15 seconds, which carry the length of the run in place of `duration`; `aspect-ratio=\"auto\"` takes their shape.",
+        pixversePromptNote,
+      ],
+    },
   },
-}] as const;
+] as const;
 
 export const pixverseManifest = {
   ...pixverseBaseDefinition.manifest,