from PIL import Image import torch from point_e.diffusion.configs import DIFFUSION_CONFIGS, diffusion_from_config from point_e.diffusion.sampler import PointCloudSampler from point_e.models.download import load_checkpoint from point_e.models.configs import MODEL_CONFIGS, model_from_config from point_e.util.plotting import plot_point_cloud from point_e.util.pc_to_mesh import marching_cubes_mesh import skimage.measure from pyntcloud import PyntCloud import matplotlib.colors import plotly.graph_objs as go import trimesh import gradio as gr state = "" device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') def set_state(s): print(s) global state state = s def get_state(): return state set_state('Creating txt2mesh model...') t2m_name = 'base40M-textvec' # 'base40M' t2m_model = model_from_config(MODEL_CONFIGS[t2m_name], device) t2m_model.eval() base_diffusion_t2m = diffusion_from_config(DIFFUSION_CONFIGS[t2m_name]) set_state('Downloading txt2mesh checkpoint...') t2m_model.load_state_dict(load_checkpoint(t2m_name, device)) def load_img2mesh_model(model_name): set_state(f'Creating img2mesh model {model_name}...') i2m_name = model_name i2m_model = model_from_config(MODEL_CONFIGS[i2m_name], device) i2m_model.eval() base_diffusion_i2m = diffusion_from_config(DIFFUSION_CONFIGS[i2m_name]) set_state(f'Downloading img2mesh checkpoint {model_name}...') i2m_model.load_state_dict(load_checkpoint(i2m_name, device)) return i2m_model, base_diffusion_i2m img2mesh_model_name = 'base40M' #'base300M' #'base1B' img2mesh_model, base_diffusion_i2m = load_img2mesh_model(img2mesh_model_name) set_state('Creating upsample model...') upsampler_model = model_from_config(MODEL_CONFIGS['upsample'], device) upsampler_model.eval() upsampler_diffusion = diffusion_from_config(DIFFUSION_CONFIGS['upsample']) set_state('Downloading upsampler checkpoint...') upsampler_model.load_state_dict(load_checkpoint('upsample', device)) set_state('Creating SDF model...') sdf_name = 'sdf' sdf_model = model_from_config(MODEL_CONFIGS[sdf_name], device) sdf_model.eval() set_state('Loading SDF model...') sdf_model.load_state_dict(load_checkpoint(sdf_name, device)) set_state('') def get_sampler(model_name, txt2obj, guidance_scale): global img2mesh_model_name global base_diffusion_i2m global img2mesh_model if model_name != img2mesh_model_name: img2mesh_model_name = model_name img2mesh_model, base_diffusion_i2m = load_img2mesh_model(model_name) return PointCloudSampler( device=device, models=[t2m_model, upsampler_model], diffusions=[base_diffusion_t2m if txt2obj else base_diffusion_i2m, upsampler_diffusion], num_points=[1024, 4096 - 1024], aux_channels=['R', 'G', 'B'], guidance_scale=[guidance_scale, 0.0 if txt2obj else guidance_scale], model_kwargs_key_filter=('texts', '') if txt2obj else ("*",) ) def generate(model_name, input, guidance_scale, grid_size): set_state('Entered generate function...') if isinstance(input, Image.Image): input = prepare_img(input) # if input is a string, it's a text prompt sampler = get_sampler(model_name, txt2obj=True if isinstance(input, str) else False, guidance_scale=guidance_scale) # Produce a sample from the model. set_state('Sampling...') samples = None kw_args = dict(texts=[input]) if isinstance(input, str) else dict(images=[input]) for x in sampler.sample_batch_progressive(batch_size=1, model_kwargs=kw_args): samples = x set_state('Converting to point cloud...') pc = sampler.output_to_point_clouds(samples)[0] set_state('Converting to mesh...') save_ply(pc, 'output.ply', grid_size) set_state('') return pc_to_plot(pc), ply_to_obj('output.ply', 'output.obj'), gr.update(value='output.obj', visible=True) def prepare_img(img): w, h = img.size if w > h: img = img.crop(((w-h)/2, 0, (w+h)/2, h)) else: img = img.crop((0, (h-w)/2, w, (h+w)/2)) # resize to 256x256 img = img.resize((256, 256)) return img def pc_to_plot(pc): return go.Figure( data=[ go.Scatter3d( x=pc.coords[:,0], y=pc.coords[:,1], z=pc.coords[:,2], mode='markers', marker=dict( size=2, color=['rgb({},{},{})'.format(r,g,b) for r,g,b in zip(pc.channels["R"], pc.channels["G"], pc.channels["B"])], ) ) ], layout=dict( scene=dict(xaxis=dict(visible=False), yaxis=dict(visible=False), zaxis=dict(visible=False)) ), ) def ply_to_obj(ply_file, obj_file): mesh = trimesh.load(ply_file) mesh.export(obj_file) return obj_file def save_ply(pc, file_name, grid_size): # Produce a mesh (with vertex colors) mesh = marching_cubes_mesh( pc=pc, model=sdf_model, batch_size=4096, grid_size=grid_size, # increase to 128 for resolution used in evals progress=True, ) # Write the mesh to a PLY file to import into some other program. with open(file_name, 'wb') as f: mesh.write_ply(f) with gr.Blocks() as app: gr.Markdown("## Point-E text-to-3D Demo") gr.Markdown("This is a demo for [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://arxiv.org/abs/2212.08751) by OpenAI. Check out the [GitHub repo](https://github.com/openai/point-e) for more information.") with gr.Row(): with gr.Column(): with gr.Tab("Text to 3D"): prompt = gr.Textbox(label="Prompt", placeholder="A cactus in a pot") btn_generate_txt2obj = gr.Button(value="Generate") with gr.Tab("Image to 3D"): img = gr.Image(label="Image") btn_generate_img2obj = gr.Button(value="Generate") with gr.Accordion("Advanced settings", open=False): dropdown_models = gr.Dropdown(label="Model", value="base40M", choices=["base40M", "base300M", "base1B"]) guidance_scale = gr.Slider(label="Guidance scale", value=3.0, minimum=3.0, maximum=10.0, step=1.0) grid_size = gr.Slider(label="Grid size", value=32, minimum=16, maximum=128, step=16) state_info = state_info = gr.Textbox(label="State", show_label=False).style(container=False) with gr.Column(): plot = gr.Plot(label="Point cloud") # btn_pc_to_obj = gr.Button(value="Convert to OBJ", visible=False) model_3d = gr.Model3D(value=None) file_out = gr.File(label="Obj file", visible=False) # inputs = [dropdown_models, prompt, img, guidance_scale, grid_size] outputs = [plot, model_3d, file_out] prompt.submit(generate, inputs=[dropdown_models, prompt, guidance_scale, grid_size], outputs=outputs) btn_generate_txt2obj.click(generate, inputs=[dropdown_models, prompt, guidance_scale, grid_size], outputs=outputs) btn_generate_img2obj.click(generate, inputs=[dropdown_models, img, guidance_scale, grid_size], outputs=outputs) # btn_pc_to_obj.click(ply_to_obj, inputs=plot, outputs=[model_3d, file_out]) gr.HTML("""

Space by:
Twitter Follow
GitHub followers


Buy Me A Coffee

visitors

""") app.load(get_state, inputs=[], outputs=state_info, every=0.5, show_progress=False) app.queue() # app.launch(debug=True, share=True, height=768) app.launch(debug=True)