Mairaaa commited on
Commit
6ae61a6
·
verified ·
1 Parent(s): a31ded7

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +89 -19
app.py CHANGED
@@ -1,25 +1,95 @@
1
- import streamlit as st
2
  import os
3
- import subprocess
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
 
5
- # Title
6
- st.title("Multimodal Garment Designer")
 
 
 
 
 
 
7
 
8
- # Input fields
9
- dataset_path = st.text_input("Dataset Path:", "./assets/data/dresscode")
10
- output_dir = st.text_input("Output Directory:", "./output")
11
- test_order = st.selectbox("Test Order:", ["paired", "unpaired"])
12
- save_name = st.text_input("Save Name:", "model_output")
13
 
14
- # Button to run the eval script
15
- if st.button("Run Evaluation"):
16
- # Construct the command
17
- command = f"python eval.py --output_dir {output_dir} --dataset_path {dataset_path} --test_order {test_order} --save_name {save_name}"
 
 
 
 
18
 
19
- # Run the command
20
- with st.spinner("Running evaluation..."):
21
- result = subprocess.run(command, shell=True, capture_output=True, text=True)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
 
23
- # Display the result
24
- st.code(result.stdout)
25
- st.code(result.stderr)
 
 
1
  import os
2
+ import torch
3
+ import streamlit as st
4
+ from diffusers import AutoencoderKL, DDIMScheduler
5
+ from transformers import CLIPTextModel, CLIPTokenizer
6
+ from src.mgd_pipelines.mgd_pipe import MGDPipe
7
+ from src.mgd_pipelines.mgd_pipe_disentangled import MGDPipeDisentangled
8
+ from src.utils.image_from_pipe import generate_images_from_mgd_pipe
9
+ from accelerate import Accelerator
10
+ from diffusers.utils import check_min_version
11
+ from src.utils.set_seeds import set_seed
12
+
13
+ # Will error if the minimal version of diffusers is not installed. Remove at your own risks.
14
+ check_min_version("0.10.0.dev0")
15
+
16
+ # Set the environment variables for Hugging Face Spaces
17
+ os.environ["TOKENIZERS_PARALLELISM"] = "true"
18
+ os.environ["WANDB_START_METHOD"] = "thread"
19
+
20
+ # Streamlit interface components
21
+ st.title("Fashion Image Generation with Multimodal Garment Designer")
22
+
23
+ # Streamlit Input Parameters
24
+ category = st.selectbox("Select Category", ["dresses", "upper_body", "lower_body", "all"])
25
+ guidance_scale = st.slider("Guidance Scale", min_value=0.1, max_value=20.0, value=7.5, step=0.1)
26
+ guidance_scale_pose = st.slider("Guidance Scale (Pose)", min_value=0.1, max_value=20.0, value=7.5, step=0.1)
27
+ guidance_scale_sketch = st.slider("Guidance Scale (Sketch)", min_value=0.1, max_value=20.0, value=7.5, step=0.1)
28
+ sketch_cond_rate = st.slider("Sketch Conditioning Rate", min_value=0.1, max_value=1.0, value=0.5, step=0.05)
29
+ start_cond_rate = st.slider("Start Conditioning Rate", min_value=0.1, max_value=1.0, value=0.5, step=0.05)
30
+ seed = st.number_input("Seed", value=42, min_value=1)
31
+
32
+ # Button to run the image generation
33
+ if st.button("Generate Image"):
34
+ # Initialize Accelerator (for mixed precision, etc.)
35
+ accelerator = Accelerator()
36
+ device = accelerator.device
37
+
38
+ # Set the seed
39
+ set_seed(seed)
40
+
41
+ # Model and Tokenizer loading (use pre-trained from Hugging Face)
42
+ model_name = "stabilityai/stable-diffusion-2-1-base" # Use appropriate model name
43
+
44
+ # Load scheduler, tokenizer, and models
45
+ val_scheduler = DDIMScheduler.from_pretrained(model_name, subfolder="scheduler")
46
+ val_scheduler.set_timesteps(50, device=device)
47
+
48
+ tokenizer = CLIPTokenizer.from_pretrained(model_name, subfolder="tokenizer")
49
+ text_encoder = CLIPTextModel.from_pretrained(model_name, subfolder="text_encoder")
50
+ vae = AutoencoderKL.from_pretrained(model_name, subfolder="vae")
51
 
52
+ # Load UNet model (you can use your own model)
53
+ unet = torch.hub.load(
54
+ dataset="aimagelab/multimodal-garment-designer",
55
+ repo_or_dir="aimagelab/multimodal-garment-designer",
56
+ source="github",
57
+ model="mgd",
58
+ pretrained=True,
59
+ )
60
 
61
+ # Freeze VAE and text encoder
62
+ vae.requires_grad_(False)
63
+ text_encoder.requires_grad_(False)
 
 
64
 
65
+ # Select pipeline (use disentangled option if needed)
66
+ val_pipe = MGDPipe(
67
+ text_encoder=text_encoder,
68
+ vae=vae,
69
+ unet=unet.to(vae.dtype),
70
+ tokenizer=tokenizer,
71
+ scheduler=val_scheduler,
72
+ ).to(device)
73
 
74
+ # Run image generation using your pipeline
75
+ with torch.no_grad():
76
+ # Generate the image
77
+ images = generate_images_from_mgd_pipe(
78
+ test_order="test", # or some predefined order
79
+ pipe=val_pipe,
80
+ test_dataloader=None, # Adjust accordingly, or use pre-existing dataset
81
+ save_name="generated_image",
82
+ dataset="dresscode", # Adjust if needed
83
+ output_dir=".", # Save location
84
+ guidance_scale=guidance_scale,
85
+ guidance_scale_pose=guidance_scale_pose,
86
+ guidance_scale_sketch=guidance_scale_sketch,
87
+ sketch_cond_rate=sketch_cond_rate,
88
+ start_cond_rate=start_cond_rate,
89
+ no_pose=False,
90
+ disentagle=False, # Adjust if needed
91
+ seed=seed,
92
+ )
93
 
94
+ # Display the generated image
95
+ st.image(images[0], caption="Generated Fashion Image", use_column_width=True)