import gradio as gr import spaces from gradio_litmodel3d import LitModel3D import os import shutil os.environ['TOKENIZERS_PARALLELISM'] = 'true' os.environ['SPCONV_ALGO'] = 'native' from typing import * import torch import numpy as np import imageio from easydict import EasyDict as edict from trellis.pipelines import TrellisTextTo3DPipeline from trellis.representations import Gaussian, MeshExtractResult from trellis.utils import render_utils, postprocessing_utils MAX_SEED = np.iinfo(np.int32).max TMP_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tmp') os.makedirs(TMP_DIR, exist_ok=True) def start_session(req: gr.Request): user_dir = os.path.join(TMP_DIR, str(req.session_hash)) os.makedirs(user_dir, exist_ok=True) def end_session(req: gr.Request): user_dir = os.path.join(TMP_DIR, str(req.session_hash)) shutil.rmtree(user_dir) def pack_state(gs: Gaussian, mesh: MeshExtractResult) -> dict: return { 'gaussian': { **gs.init_params, '_xyz': gs._xyz.cpu().numpy(), '_features_dc': gs._features_dc.cpu().numpy(), '_scaling': gs._scaling.cpu().numpy(), '_rotation': gs._rotation.cpu().numpy(), '_opacity': gs._opacity.cpu().numpy(), }, 'mesh': { 'vertices': mesh.vertices.cpu().numpy(), 'faces': mesh.faces.cpu().numpy(), }, } def unpack_state(state: dict) -> Tuple[Gaussian, edict, str]: gs = Gaussian( aabb=state['gaussian']['aabb'], sh_degree=state['gaussian']['sh_degree'], mininum_kernel_size=state['gaussian']['mininum_kernel_size'], scaling_bias=state['gaussian']['scaling_bias'], opacity_bias=state['gaussian']['opacity_bias'], scaling_activation=state['gaussian']['scaling_activation'], ) gs._xyz = torch.tensor(state['gaussian']['_xyz'], device='cuda') gs._features_dc = torch.tensor(state['gaussian']['_features_dc'], device='cuda') gs._scaling = torch.tensor(state['gaussian']['_scaling'], device='cuda') gs._rotation = torch.tensor(state['gaussian']['_rotation'], device='cuda') gs._opacity = torch.tensor(state['gaussian']['_opacity'], device='cuda') mesh = edict( vertices=torch.tensor(state['mesh']['vertices'], device='cuda'), faces=torch.tensor(state['mesh']['faces'], device='cuda'), ) return gs, mesh def get_seed(randomize_seed: bool, seed: int) -> int: return np.random.randint(0, MAX_SEED) if randomize_seed else seed @spaces.GPU def text_to_3d( prompt: str, seed: int, ss_guidance_strength: float, ss_sampling_steps: int, slat_guidance_strength: float, slat_sampling_steps: int, req: gr.Request, ) -> Tuple[dict, str]: user_dir = os.path.join(TMP_DIR, str(req.session_hash)) outputs = pipeline.run( prompt, seed=seed, formats=["gaussian", "mesh"], sparse_structure_sampler_params={ "steps": ss_sampling_steps, "cfg_strength": ss_guidance_strength, }, slat_sampler_params={ "steps": slat_sampling_steps, "cfg_strength": slat_guidance_strength, }, ) video = render_utils.render_video(outputs['gaussian'][0], num_frames=120)['color'] video_geo = render_utils.render_video(outputs['mesh'][0], num_frames=120)['normal'] video = [np.concatenate([video[i], video_geo[i]], axis=1) for i in range(len(video))] video_path = os.path.join(user_dir, 'sample.mp4') imageio.mimsave(video_path, video, fps=15) state = pack_state(outputs['gaussian'][0], outputs['mesh'][0]) torch.cuda.empty_cache() return state, video_path @spaces.GPU def extract_glb( state: dict, mesh_simplify: float, texture_size: int, req: gr.Request, ) -> Tuple[str, str]: user_dir = os.path.join(TMP_DIR, str(req.session_hash)) gs, mesh = unpack_state(state) glb = postprocessing_utils.to_glb(gs, mesh, simplify=mesh_simplify, texture_size=texture_size, verbose=False) glb_path = os.path.join(user_dir, 'sample.glb') glb.export(glb_path) torch.cuda.empty_cache() return glb_path, glb_path with gr.Blocks(delete_cache=(600, 600)) as demo: gr.Markdown(""" # UTPL - Conversión de Texto a objetos 3D usando IA ### Tesis: *"Objetos tridimensionales creados por IA: Innovación en entornos virtuales"* **Autor:** Carlos Vargas **Base técnica:** Adaptación de [TRELLIS](https://trellis3d.github.io/) (herramienta de código abierto para generación 3D) **Propósito educativo:** Demostraciones académicas e Investigación en modelado 3D automático """) with gr.Row(): with gr.Column(): text_prompt = gr.Textbox(label="Text Prompt", lines=5) with gr.Accordion(label="Generation Settings", open=False): seed = gr.Slider(0, MAX_SEED, label="Seed", value=0, step=1) randomize_seed = gr.Checkbox(label="Randomize Seed", value=True) with gr.Row(): ss_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=7.5, step=0.1) ss_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=25, step=1) with gr.Row(): slat_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=7.5, step=0.1) slat_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=25, step=1) generate_btn = gr.Button("Generate") with gr.Accordion(label="GLB Extraction Settings", open=False): mesh_simplify = gr.Slider(0.9, 0.98, label="Simplify", value=0.95, step=0.01) texture_size = gr.Slider(512, 2048, label="Texture Size", value=1024, step=512) with gr.Row(): extract_glb_btn = gr.Button("Extract GLB", interactive=False) with gr.Column(scale=3, min_width=600): with gr.Group(): video_output = gr.Video( label="3D Preview", autoplay=True, loop=True, height=300, show_label=False ) model_output = gr.Model3D( label="3D Model Viewer", height=400 ) with gr.Row(): download_glb = gr.DownloadButton( label="Download GLB File", interactive=False, variant="secondary", size="lg" ) output_buf = gr.State() # Handlers demo.load(start_session) demo.unload(end_session) generate_btn.click( get_seed, inputs=[randomize_seed, seed], outputs=[seed], ).then( text_to_3d, inputs=[text_prompt, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps], outputs=[output_buf, video_output], ).then( lambda: gr.Button(interactive=True), outputs=[extract_glb_btn], ) video_output.clear( lambda: gr.Button(interactive=False), outputs=[extract_glb_btn], ) extract_glb_btn.click( extract_glb, inputs=[output_buf, mesh_simplify, texture_size], outputs=[model_output, download_glb], ).then( lambda: gr.Button(interactive=True), outputs=[download_glb], ) model_output.clear( lambda: gr.Button(interactive=False), outputs=[download_glb], ) # Launch the Gradio app if __name__ == "__main__": pipeline = TrellisTextTo3DPipeline.from_pretrained("cavargas10/TRELLIS-text-xlarge") pipeline.cuda() demo.launch()