94b8726ffb
Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01WV6BzHQiJEvvK9EPc1d4ks
197 lines
10 KiB
TOML
197 lines
10 KiB
TOML
[package]
|
|
name = "makepad-ai-hub"
|
|
version = "0.3.0"
|
|
edition = "2021"
|
|
description = "AI content generation service: wraps local GPU model runtimes (image/mesh/video/audio) behind an HTTP port, with on-demand HuggingFace model download"
|
|
license = "MIT OR Apache-2.0"
|
|
|
|
# Standalone workspace: this crate pulls in platform/network and the
|
|
# per-family model crates under libs/ai, so it stays out of the root
|
|
# workspace member list.
|
|
[workspace]
|
|
|
|
[features]
|
|
# Native backends only. Python/Torch oracles stay off unless a box
|
|
# explicitly enables `python-backends`.
|
|
default = [
|
|
"flux",
|
|
"paint",
|
|
"paint-cuda",
|
|
"llm",
|
|
"tts",
|
|
"indextts",
|
|
"speech",
|
|
"stt",
|
|
"video",
|
|
"interpolate",
|
|
"audio",
|
|
"mesh",
|
|
"matte-native",
|
|
"depth-native",
|
|
"segment-native",
|
|
"body-native",
|
|
"upscale-native",
|
|
"motion-native",
|
|
"rig-native",
|
|
"splat-native",
|
|
"beats-native",
|
|
"stems-native",
|
|
"notes-native",
|
|
]
|
|
# Box-provisioned Python/Torch reference backends (FlashWorld, Music3,
|
|
# Depth-Anything-3, and the rig/motion oracles). Not in default: a native
|
|
# service must not advertise or instantiate a Python runtime.
|
|
python-backends = []
|
|
# Real Flux image generation via makepad-ai-flux.
|
|
flux = ["dep:makepad-ai-flux", "dep:makepad-ai-common"]
|
|
# The generative-PBR paint domain: mesh GLB + reference image -> PBR-textured
|
|
# GLB + semantic maps + provenance manifest. Ships the deterministic
|
|
# "paint-test" tier everywhere. Default also enables `paint-cuda`, so a
|
|
# Windows/Linux fleet box advertises Hunyuan Paint and downloads weights
|
|
# like any other registry model.
|
|
paint = ["dep:makepad-ai-paint", "dep:makepad-gltf", "dep:makepad-remesh", "dep:makepad-xatlas"]
|
|
# Windows/Linux CUDA Hunyuan executor (in default).
|
|
paint-cuda = ["paint", "makepad-ai-paint/cuda-taps"]
|
|
# Real LLM prompt expansion via makepad-ai-llm (Qwen3.5/3.6 GGUF).
|
|
llm = ["dep:makepad-ai-llm"]
|
|
# Speech sessions (AiHub::start_stt / start_tts): the OS engines as the
|
|
# stt.system / tts.system pipes plus the in-process / machine / LAN ladder.
|
|
speech = ["dep:makepad-system-speech"]
|
|
# Whisper speech-to-text (stt.whisper), in-process and on the wire.
|
|
stt = ["speech", "dep:makepad-ai-speech", "makepad-ai-speech/whisper"]
|
|
# Real Kokoro speech synthesis via makepad-ai-speech.
|
|
tts = ["dep:makepad-ai-speech", "makepad-ai-speech/kokoro"]
|
|
# Real IndexTTS-2.5 character-voice TTS via makepad-ai-speech.
|
|
indextts = ["dep:makepad-ai-speech", "makepad-ai-speech/indextts", "dep:makepad-ai-common"]
|
|
# Real MiniMax H3 video generation via makepad-ai-h3 plus the hardware
|
|
# video file encoder (makepad-platform-video). Does NOT pull the UI platform crate.
|
|
video = ["dep:makepad-ai-h3", "dep:makepad-ai-common", "dep:makepad-video"]
|
|
# Native Practical-RIFE v4.26 frame interpolation as an optional post-stage
|
|
# of the video backend (`interpolate: 2|4`). Independent of `video`: the
|
|
# stage sits after the generator, so the stubbed CI video path exercises it
|
|
# too. Weights ride along with each H3 tier through the "interpolate" file
|
|
# role, so the domain never grows a second selectable model.
|
|
interpolate = ["dep:makepad-ai-rife", "dep:makepad-ai-common"]
|
|
# Real SA3 / MOSS / Woosh / ACE / Music3 audio via the sfx + music crates.
|
|
audio = ["dep:makepad-ai-sfx", "dep:makepad-ai-music", "dep:makepad-ai-common"]
|
|
# Real TRELLIS.2 image->GLB via makepad-ai-trellis plus the in-repo remesher.
|
|
# Also needs H3's noise helper and BiRefNet (via matte-native).
|
|
mesh = ["matte-native", "depth-native", "dep:makepad-ai-trellis", "dep:makepad-ai-h3", "dep:makepad-ai-common", "dep:makepad-remesh", "dep:makepad-gltf", "dep:makepad-xatlas"]
|
|
# Native BiRefNet image matting. Separate from `mesh` so a matte-only
|
|
# service does not pull TRELLIS/remesh.
|
|
matte-native = ["dep:makepad-ai-vision", "dep:makepad-ai-common"]
|
|
# Native DA3METRIC-LARGE metric depth. Independent of `mesh`.
|
|
depth-native = ["dep:makepad-ai-vision", "dep:makepad-ai-common"]
|
|
# Native SAM 3.1 multiplex segmentation. Independent of `mesh`.
|
|
segment-native = ["dep:makepad-ai-vision", "dep:makepad-ai-common"]
|
|
# Native SAM 3D Body pose estimation.
|
|
body-native = ["dep:makepad-ai-body", "dep:makepad-ai-common"]
|
|
# Native RealESRGAN x4plus general-image upscaling. Independent of `mesh`.
|
|
upscale-native = ["dep:makepad-ai-vision", "dep:makepad-ai-common"]
|
|
# Native HY-Motion decode -> rig retarget -> animated GLB.
|
|
motion-native = ["dep:makepad-ai-motion", "dep:makepad-ai-common", "dep:makepad-gltf", "dep:makepad-render"]
|
|
# Native TripoSplat image -> 3D gaussian splat. Needs BiRefNet (via
|
|
# matte-native) for the cutout and the FLUX.2 VAE encoder (via the flux
|
|
# family crate, which makepad-ai-splat depends on directly).
|
|
splat-native = ["matte-native", "dep:makepad-ai-splat", "dep:makepad-ai-common"]
|
|
# Native SkinTokens checkpoint conversion, inference, surface transfer and
|
|
# lossless skinned-GLB augmentation. The reference Torch/bpy backend remains
|
|
# separately available as `rig-oracle` through `python-backends`.
|
|
rig-native = ["dep:makepad-ai-rig", "dep:makepad-ai-common", "dep:makepad-gltf"]
|
|
# In-process registry/downloader/backend runner for desktop applications.
|
|
# Opt-in so featureless fleet clients do not pull the GPU model substrate.
|
|
local = ["dep:makepad-ai-common"]
|
|
# Native Beat This! audio -> beat/downbeat JSON analysis.
|
|
beats-native = ["dep:makepad-ai-beats", "dep:makepad-ai-common"]
|
|
# Native BS-RoFormer music source separation. Clients use the featureless hub
|
|
# slice; only fleet service builds compile and load this model.
|
|
stems-native = ["dep:makepad-ai-stems", "dep:makepad-ai-common"]
|
|
# Native Spotify Basic Pitch audio -> notes/MIDI transcription. The model is
|
|
# tiny and has a CPU fallback, so this lane is available without a GPU.
|
|
notes-native = ["dep:makepad-ai-notes"]
|
|
|
|
[dependencies]
|
|
makepad-micro-serde = { path = "../../micro_serde" }
|
|
makepad-base64 = { path = "../../base64" }
|
|
makepad-network = { path = "../../../platform/network" }
|
|
makepad-strict-json = { path = "../../strict_json" }
|
|
# Reuse-group UDP bind for the fleet beacon listener (several apps on one
|
|
# machine listen at once); the client crate owns that socket helper.
|
|
makepad-asset-client = { path = "../../asset/client" }
|
|
makepad-zune-core = { path = "../../zune/zune-core" }
|
|
makepad-zune-png = { path = "../../zune/zune-png" }
|
|
# Vision-domain request images arrive as PNG or JPEG.
|
|
makepad-zune-jpeg = { path = "../../zune/zune-jpeg" }
|
|
makepad-zip-file = { path = "../../zip_file" }
|
|
# Music reference clips arrive as any audio file the in-repo decoders read
|
|
# (MP3 / FLAC / Ogg Vorbis here, WAV in crate::wav). No deps, no unsafe.
|
|
makepad-audio-decode = { path = "../../audio_decode" }
|
|
makepad-ai-common = { path = "../../ai/models/common", optional = true }
|
|
makepad-ai-flux = { path = "../../ai/models/flux", optional = true }
|
|
makepad-ai-h3 = { path = "../../ai/models/h3", optional = true }
|
|
makepad-ai-rife = { path = "../../ai/models/rife", optional = true }
|
|
makepad-ai-vision = { path = "../../ai/models/vision", optional = true }
|
|
makepad-ai-body = { path = "../models/body", optional = true }
|
|
makepad-ai-rig = { path = "../../ai/models/rig", optional = true }
|
|
makepad-ai-motion = { path = "../../ai/models/motion", optional = true }
|
|
makepad-ai-sfx = { path = "../../ai/models/sfx", optional = true }
|
|
makepad-ai-music = { path = "../../ai/models/music", optional = true }
|
|
makepad-ai-trellis = { path = "../../ai/models/trellis", optional = true }
|
|
makepad-ai-splat = { path = "../../ai/models/splat", optional = true }
|
|
makepad-ai-paint = { path = "../../ai/models/paint", optional = true }
|
|
makepad-remesh = { path = "../../remesh", optional = true }
|
|
makepad-gltf = { path = "../../gltf", optional = true }
|
|
makepad-xatlas = { path = "../../xatlas", optional = true }
|
|
makepad-render = { path = "../../render", optional = true }
|
|
makepad-ai-llm = { path = "../../ai/llm", optional = true }
|
|
makepad-ai-speech = { path = "../../ai/models/speech", default-features = false, optional = true }
|
|
makepad-ai-beats = { path = "../../ai/models/beats", optional = true }
|
|
makepad-ai-stems = { path = "../../ai/models/stems", optional = true }
|
|
makepad-ai-notes = { path = "../../ai/models/notes", optional = true }
|
|
makepad-system-speech = { path = "../../system_speech", optional = true }
|
|
makepad-video = { package = "makepad-platform-video", path = "../../../platform/video", optional = true }
|
|
# The `mkfl` motion payload: ONE definition, shared with the VJ's import
|
|
# converter (which fills the same box from a classical, model-free flow
|
|
# field). Default features off — the enhance stage owns its own codec seam
|
|
# and only needs the format.
|
|
makepad-video-flow = { path = "../../video_flow", default-features = false }
|
|
|
|
[dev-dependencies]
|
|
# Test-only: tests/service_e2e.rs drives the realtime websocket endpoint
|
|
# through the in-repo plain-TCP websocket client.
|
|
makepad-live-id = { path = "../../live_id" }
|
|
# Test-only: the h264 realtime round-trip test acts as its own client,
|
|
# encoding/decoding with the same hardware codec seam the service uses
|
|
# internally (behind the crate's own optional/default `video` feature).
|
|
makepad-video = { package = "makepad-platform-video", path = "../../../platform/video" }
|
|
|
|
# The standing "is chat slow right now?" check. Its own code is std-only —
|
|
# no HTTP or JSON crate — so what it measures is the box, not a client
|
|
# library, and it keeps working when the wire grows fields it has never
|
|
# heard of.
|
|
[[bin]]
|
|
name = "chat-bench"
|
|
path = "src/bin/chat_bench.rs"
|
|
|
|
# The standing "where does a long conversation go insane, and which subsystem
|
|
# did it?" gate. Two arms per rung — one cold request at depth against the same
|
|
# content grown turn by turn — so a failure names the incremental path or the
|
|
# position/arena math instead of just saying "long contexts are bad". Std-only
|
|
# for the same reason chat-bench is.
|
|
[[bin]]
|
|
name = "context-ladder"
|
|
path = "src/bin/context_ladder.rs"
|
|
|
|
# The OCR bench: every page image in a directory through the resident ocr
|
|
# backend (local weights) or through a box's wire, one HTML per page, and
|
|
# the numbers that decide the model — seconds per page, image/output tokens,
|
|
# retries — plus `--score` to rank transcriptions against a reference.
|
|
[[bin]]
|
|
name = "ocr-bench"
|
|
path = "src/bin/ocr_bench.rs"
|
|
|
|
# TTS -> STT through the hub's own speech sessions, scored as word error rate:
|
|
# the scoreboard for comparing engines and the end-to-end check of the ladder.
|
|
[[bin]]
|
|
name = "speech-roundtrip"
|
|
path = "src/bin/speech_roundtrip.rs"
|