app_texnet.py

#!/usr/bin/env python

import os
import shutil
import tempfile
import gradio as gr
from PIL import Image
import numpy as np

from settings import (
    DEFAULT_IMAGE_RESOLUTION,
    DEFAULT_NUM_IMAGES,
    MAX_IMAGE_RESOLUTION,
    MAX_NUM_IMAGES,
    MAX_SEED,
)
from utils import randomize_seed_fn

# ---- helper to build a quick textured copy of the mesh ---------------
def apply_texture(src_mesh:str, texture:str, tag:str)->str:
    """
    Writes a copy of `src_mesh` and tiny .mtl that points to `texture`.
    Returns the new OBJ/GLB path for viewing.
    """
    tmp_dir = tempfile.mkdtemp()
    mesh_copy = os.path.join(tmp_dir, f"{tag}.obj")
    mtl_name  = f"{tag}.mtl"

    # copy geometry
    shutil.copy(src_mesh, mesh_copy)

    # write minimal MTL
    with open(os.path.join(tmp_dir, mtl_name), "w") as f:
        f.write(f"newmtl material_0\nmap_Kd {os.path.basename(texture)}\n")

    # ensure texture lives next to OBJ
    shutil.copy(texture, os.path.join(tmp_dir, os.path.basename(texture)))

    # patch OBJ to reference our new MTL
    with open(mesh_copy, "r+") as f:
        lines = f.readlines()
        if not lines[0].startswith("mtllib"):
            lines.insert(0, f"mtllib {mtl_name}\n")
            f.seek(0); f.writelines(lines)

    return mesh_copy

def image_to_temp_path(img_like, tag):
    """
    Convert various image-like objects (str, PIL.Image, list, tuple) to temp PNG path.
    Returns the path to the saved image file.
    """
    # Handle tuple or list input
    if isinstance(img_like, (list, tuple)):
        if len(img_like) == 0:
            raise ValueError("Empty image list/tuple.")
        img_like = img_like[0]

    # If it's already a file path
    if isinstance(img_like, str):
        return img_like

    # If it's a PIL Image
    if isinstance(img_like, Image.Image):
        temp_path = os.path.join(tempfile.mkdtemp(), f"{tag}.png")
        img_like.save(temp_path)
        return temp_path

    # if it's numpy array
    if isinstance(img_like, np.ndarray):
        temp_path = os.path.join(tempfile.mkdtemp(), f"{tag}.png")
        img_like = Image.fromarray(img_like)
        img_like.save(temp_path)
        return temp_path

    raise ValueError(f"Expected PIL.Image, str, list, or tuple — got {type(img_like)}")

def show_mesh(which, mesh, inp, coarse, fine):
    """Switch the displayed texture based on dropdown change."""
    print()
    tex_map = {
        "Input": image_to_temp_path(inp, "input"),
        "Coarse": coarse[0] if isinstance(coarse, tuple) else coarse,
        "Fine": fine[0] if isinstance(fine, tuple) else fine,
    }
    texture_path = tex_map[which]
    return apply_texture(mesh, texture_path, which.lower())
# ----------------------------------------------------------------------


def create_demo(process):
    with gr.Blocks() as demo:
        with gr.Row():
            with gr.Column():
                gr.Markdown("## Select preset from the example list, and modify the prompt accordingly")
                with gr.Row():
                    name = gr.Textbox(label="Name", interactive=False, visible=False)
                    representative = gr.Image(label="Geometry", interactive=False)
                    image = gr.Image(label="UV Normal", interactive=False)
                prompt = gr.Textbox(label="Prompt", submit_btn=True)
                with gr.Accordion("Advanced options", open=False):
                    num_samples = gr.Slider(
                        label="Number of images", minimum=1, maximum=MAX_NUM_IMAGES, value=DEFAULT_NUM_IMAGES, step=1
                    )
                    image_resolution = gr.Slider(
                        label="Image resolution",
                        minimum=256,
                        maximum=MAX_IMAGE_RESOLUTION,
                        value=DEFAULT_IMAGE_RESOLUTION,
                        step=256,
                    )
                    num_steps = gr.Slider(label="Number of steps", minimum=1, maximum=100, value=10, step=1)
                    guidance_scale = gr.Slider(label="Guidance scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
                    seed = gr.Slider(label="Seed", minimum=0, maximum=MAX_SEED, step=1, value=0)
                    randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
                    a_prompt = gr.Textbox(label="Additional prompt", value="best quality, extremely detailed")
                    n_prompt = gr.Textbox(
                        label="Negative prompt",
                        value="longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",
                    )
            with gr.Column():
                # 2x2 grid of images for the output textures
                gr.Markdown("### Output BRDF")
                with gr.Row():
                    base_color = gr.Gallery(label="Base Color", show_label=True, columns=1, object_fit="scale-down")
                    normal = gr.Gallery(label="Displacement Map", show_label=True, columns=1, object_fit="scale-down")
                with gr.Row():
                    roughness = gr.Gallery(label="Roughness Map", show_label=True, columns=1, object_fit="scale-down")
                    metallic = gr.Gallery(label="Metallic Map", show_label=True, columns=1, object_fit="scale-down")
                
                gr.Markdown("### Download Packed Blender Files for 3D Visualization")
                out_blender_path = gr.File(label="Generated Blender File", file_types=[".blend"])

        inputs = [
            name,  # Name of the object
            representative,  # Geometry mesh
            image,
            prompt,
            a_prompt,
            n_prompt,
            num_samples,
            image_resolution,
            num_steps,
            guidance_scale,
            seed,
        ]
        
        # first call → run diffusion / texture network
        prompt.submit(
            fn=randomize_seed_fn,
            inputs=[seed, randomize_seed],
            outputs=seed,
            queue=False,
            api_name=False,
        ).then(
            fn=process,
            inputs=inputs,
            outputs=[base_color, normal, roughness, metallic, out_blender_path],
            api_name="canny",
            concurrency_id="main",
        )

        gr.Examples(
            fn=process,
            inputs=inputs,
            outputs=[base_color, normal, roughness, metallic],
            examples=[
                [
                    "bunny",
                    "examples/bunny/frame_0001.png", # /dgxusers/Users/jyang/project/ObjectReal/data/control/preprocess/bunny/uv_normal/fused.png
                    "examples/bunny/uv_normal.png", # /dgxusers/Users/jyang/project/ObjectReal/data/control/preprocess/bunny/uv_normal/fused.png
                    "feather", 
                    a_prompt.value, 
                    n_prompt.value,
                    num_samples.value,
                    image_resolution.value,
                    num_steps.value,
                    guidance_scale.value,
                    seed.value,
                ],
                [
                    "monkey",
                    "examples/monkey/frame_0001.png", # /dgxusers/Users/jyang/project/ObjectReal/data/control/preprocess/monkey/uv_normal/fused.png
                    "examples/monkey/uv_normal.png", # /dgxusers/Users/jyang/project/ObjectReal/data/control/preprocess/monkey/uv_normal/fused.png
                    "wood", 
                    a_prompt.value, 
                    n_prompt.value,
                    num_samples.value,
                    image_resolution.value,
                    num_steps.value,
                    guidance_scale.value,
                    seed.value,
                ],
                [
                    "tshirt",
                    "examples/tshirt/frame_0001.png", # /dgxusers/Users/jyang/project/ObjectReal/data/control/preprocess/monkey/uv_normal/fused.png
                    "examples/tshirt/uv_normal.png", # /dgxusers/Users/jyang/project/ObjectReal/data/control/preprocess/monkey/uv_normal/fused.png
                    "wood", 
                    a_prompt.value, 
                    n_prompt.value,
                    num_samples.value,
                    image_resolution.value,
                    num_steps.value,
                    guidance_scale.value,
                    seed.value,
                ],
                [
                    "highheel",
                    "examples/highheel/frame_0001.png", # /dgxusers/Users/jyang/project/ObjectReal/data/control/preprocess/monkey/uv_normal/fused.png
                    "examples/highheel/uv_normal.png", # /dgxusers/Users/jyang/project/ObjectReal/data/control/preprocess/monkey/uv_normal/fused.png
                    "wood", 
                    a_prompt.value, 
                    n_prompt.value,
                    num_samples.value,
                    image_resolution.value,
                    num_steps.value,
                    guidance_scale.value,
                    seed.value,
                ],
                [
                    "tank",
                    "examples/tank/frame_0001.png", # /dgxusers/Users/jyang/project/ObjectReal/data/control/preprocess/monkey/uv_normal/fused.png
                    "examples/tank/uv_normal.png", # /dgxusers/Users/jyang/project/ObjectReal/data/control/preprocess/monkey/uv_normal/fused.png
                    "wood", 
                    a_prompt.value, 
                    n_prompt.value,
                    num_samples.value,
                    image_resolution.value,
                    num_steps.value,
                    guidance_scale.value,
                    seed.value,
                ],
            ],
        )

    return demo


if __name__ == "__main__":
    from model import Model

    model = Model(task_name="Texnet")
    demo = create_demo(model.process_texnet)
    demo.queue().launch()