stream-diffusion-rs/Cargo.toml at clean · compiling-org/stream-diffusion-rs · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
[package]
name = "stream-diffusion-rs"
version = "0.1.0"
edition = "2021"
description = "Stream diffusion implementation in Rust using Burn framework"
authors = ["Kapil"]
license = "MIT"
repository = "https://github.com/compiling-org/stream-diffusion-rust"
homepage = "https://github.com/compiling-org/stream-diffusion-rust"
keywords = ["ml", "diffusion", "ai", "stream", "burn"]
categories = ["science", "multimedia", "api-bindings"]

[dependencies]
# ONNX runtime for model inference
ort = "1.16"

# Native Rust deep learning frameworks (essential for ML)
# Burn - Comprehensive DL framework with multiple backends
burn = { version = "0.16", features = ["ndarray", "train", "metrics"], default-features = false, optional = true }

# PyTorch bindings - Version compatible with libtorch
tch = { version = "0.17", optional = true }

# Data serialization - Pin compatible bincode version for burn
bincode = "1.3.3"

# Data processing and ML utilities
ndarray = { version = "0.15", features = ["serde"] }
ndarray-stats = "0.5"
ndarray-rand = "0.14"
rand = "0.8"

# Visualization
plotters = { version = "0.3", default-features = false, features = ["svg_backend", "bitmap_backend", "line_series"] }

# Audio processing for audiovisual conversion
rodio = "0.17"
hound = "3.5"  # WAV file handling

# Image processing
image = "0.24"

# Async runtime for streaming and web server
tokio = { version = "1.0", features = ["full", "rt-multi-thread"] }

# Error handling
anyhow = "1.0"
thiserror = "1.0"

# Serialization for model configs
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"

# Logging
log = "0.4"
env_logger = "0.10"

# Web interface
axum = { version = "0.7", features = ["multipart", "macros"] }
tower = "0.4"
tower-http = { version = "0.5", features = ["cors"] }
mime_guess = "2.0"
chrono = { version = "0.4.42", features = ["serde"] }

# Lazy static initialization
once_cell = "1.19"

[features]
# Enable all ML features by default (excluding tch for now to avoid conflicts)
default = ["full"]
full = [
    "burn-ml",        # Use burn ML capabilities
]
# Keep individual features available for specific use cases
burn-ml = ["dep:burn"]
tch-ml = ["dep:tch"]  # Enable PyTorch integration

[profile.release]
opt-level = 3
lto = true
codegen-units = 1
panic = "abort"
strip = true

[[bin]]
name = "ui_analyzer"
path = "src/bin/ui_analyzer.rs"

[[bin]]
name = "advanced_ui_analyzer"
path = "src/bin/advanced_ui_analyzer.rs"

[[bin]]
name = "ui_fixer"
path = "src/bin/ui_fixer.rs"

[[bin]]
name = "test_python_integration"
path = "src/bin/test_python_integration.rs"

[[bin]]
name = "train_diffusion_model"
path = "src/bin/train_diffusion_model.rs"

[[bin]]
name = "ai_3d_demo"
path = "examples/ai_3d_demo.rs"

[[bin]]
name = "gesture_analyzer"
path = "src/bin/gesture_analyzer.rs"

[[bin]]
name = "gesture_fixer"
path = "src/bin/gesture_fixer.rs"

[[bin]]
name = "synesthetic_demo"
path = "examples/synesthetic_demo.rs"

[[bin]]
name = "comprehensive_ai_demo"
path = "examples/comprehensive_ai_demo.rs"