upgrade to Gradio 4.14.0

.gitignore

@@ -17,4 +17,6 @@ dist
 *egg-info
 *.so
 run.sh
-*.log
+*.log
+gradio_cached_examples
+!output.log

README.md

@@ -5,10 +5,10 @@ emoji: 🤼
 colorFrom: green
 colorTo: pink
 sdk: gradio
-sdk_version: 3.50.2
+sdk_version: 4.14.0
 app_file: app.py
 pinned: true
-python_version: 4.14.0
+python_version: 3.8.15
 ---
 
 # Unconstrained & Detailed Clothed Human Digitization (ECON + ControlNet) 

app.py

@@ -1,6 +1,5 @@
 # install
 
-import glob
 import gradio as gr
 import os
 
@@ -8,10 +7,13 @@ import subprocess
 
 if os.getenv('SYSTEM') == 'spaces':
     # subprocess.run('pip install pyembree'.split())
-    subprocess.run(
-        'pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py38_cu116_pyt1130/download.html'
-        .split()
-    )
+    try:
+        import pytorch3d
+    except ImportError:
+        subprocess.run(
+            'pip install --no-index --no-cache-dir pytorch3d -f https://dl.fbaipublicfiles.com/pytorch3d/packaging/wheels/py38_cu116_pyt1130/download.html'
+            .split()
+        )
     subprocess.run("python setup.py build_ext --inplace".split(), cwd="./lib/common/libmesh/")
     subprocess.run("python setup.py build_ext --inplace".split(), cwd="./lib/common/libvoxelize/")
 
@@ -19,37 +21,12 @@ from apps.infer import generate_model, generate_video
 
 # running
 
-description = '''
+title = '''
 # Unconstrained & Detailed Clothed Human Digitization (ECON + ControlNet) 
 ### ECON: Explicit Clothed humans Optimized via Normal integration (CVPR 2023, Highlight)
+'''
 
-<table>
-<th width="20%">
-<ul>
-<li><strong>Homepage</strong> <a href="https://econ.is.tue.mpg.de/">econ.is.tue.mpg.de</a></li>
-<li><strong>Code</strong> <a href="https://github.com/YuliangXiu/ECON">YuliangXiu/ECON</a></li>
-<li><strong>Paper</strong> <a href="https://arxiv.org/abs/2212.07422">arXiv</a>, <a href="https://readpaper.com/paper/4736821012688027649">ReadPaper</a></li>
-<li><strong>Chatroom</strong> <a href="https://discord.gg/Vqa7KBGRyk">Discord</a></li>
-</ul>
-<br>
-<ul>
-<li><strong>Colab Notebook</strong> <a href='https://colab.research.google.com/drive/1YRgwoRCZIrSB2e7auEWFyG10Xzjbrbno?usp=sharing'><img style="display: inline-block;" src='https://colab.research.google.com/assets/colab-badge.svg' alt='Google Colab'></a></li>
-<li><strong>Blender Plugin</strong> <a href='https://carlosedubarreto.gumroad.com/l/CEB_ECON'><img style="display: inline-block;" src='https://img.shields.io/badge/Blender-F6DDCC.svg?logo=Blender' alt='Blender'></a></li>
-<li><strong>Docker Image</strong> <a href='https://github.com/YuliangXiu/ECON/blob/master/docs/installation-docker.md'><img style="display: inline-block;" src='https://img.shields.io/badge/Docker-9cf.svg?logo=Docker' alt='Docker'></a></li>
-<li><strong>Windows Setup</strong> <a href="https://github.com/YuliangXiu/ECON/blob/master/docs/installation-windows.md"><img style="display: inline-block;" src='https://img.shields.io/badge/Windows-00a2ed.svg?logo=Windows' akt='Windows'></a></li>
-</ul>
-
-<br>
-<a href="https://twitter.com/yuliangxiu"><img alt="Twitter Follow" src="https://img.shields.io/twitter/follow/yuliangxiu?style=social"></a><br>
-<iframe src="https://ghbtns.com/github-btn.html?user=yuliangxiu&repo=ECON&type=star&count=true&v=2&size=small" frameborder="0" scrolling="0" width="100" height="20"></iframe>
-</th>
-<th width="40%">
-<iframe width="560" height="315" src="https://www.youtube.com/embed/5PEd_p90kS0" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
-</th>
-<th width="40%">
-<iframe width="560" height="315" src="https://www.youtube.com/embed/sbWZbTf6ZYk" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
-</th>
-</table>
+bottom = '''
 
 
 #### Citation
@@ -90,10 +67,40 @@ description = '''
 <center>
 <a href="https://huggingface.co/spaces/Yuliang/ECON?duplicate=true"><img src="https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-lg-dark.svg"/></a>
 <h2> Generate pose & prompt-guided images / Upload photos /  Use examples &rarr; Submit Image (~3min) &rarr; Generate Video (~3min) </h2>
-<h2><span style="color:red">ECON is only suitable for humanoid images and will not work well on cartoons with non-human shapes.</span></h2>
+<h2><span style="color:red">ECON is only suitable for "humanoid images" and will not work well on cartoons with non-human shapes.</span></h2>
 </center>
 '''
 
+description = '''
+<table>
+<th width="20%">
+<ul>
+<li><strong>Homepage</strong> <a href="https://econ.is.tue.mpg.de/">econ.is.tue.mpg.de</a></li>
+<li><strong>Code</strong> <a href="https://github.com/YuliangXiu/ECON">YuliangXiu/ECON</a></li>
+<li><strong>Paper</strong> <a href="https://arxiv.org/abs/2212.07422">arXiv</a>, <a href="https://readpaper.com/paper/4736821012688027649">ReadPaper</a></li>
+<li><strong>Chatroom</strong> <a href="https://discord.gg/Vqa7KBGRyk">Discord</a></li>
+</ul>
+<br>
+<ul>
+<li><strong>Colab Notebook</strong> <a href='https://colab.research.google.com/drive/1YRgwoRCZIrSB2e7auEWFyG10Xzjbrbno?usp=sharing'><img style="display: inline-block;" src='https://colab.research.google.com/assets/colab-badge.svg' alt='Google Colab'></a></li>
+<li><strong>Blender Plugin</strong> <a href='https://carlosedubarreto.gumroad.com/l/CEB_ECON'><img style="display: inline-block;" src='https://img.shields.io/badge/Blender-F6DDCC.svg?logo=Blender' alt='Blender'></a></li>
+<li><strong>Docker Image</strong> <a href='https://github.com/YuliangXiu/ECON/blob/master/docs/installation-docker.md'><img style="display: inline-block;" src='https://img.shields.io/badge/Docker-9cf.svg?logo=Docker' alt='Docker'></a></li>
+<li><strong>Windows Setup</strong> <a href="https://github.com/YuliangXiu/ECON/blob/master/docs/installation-windows.md"><img style="display: inline-block;" src='https://img.shields.io/badge/Windows-00a2ed.svg?logo=Windows' akt='Windows'></a></li>
+</ul>
+
+<br>
+<a href="https://twitter.com/yuliangxiu"><img alt="Twitter Follow" src="https://img.shields.io/twitter/follow/yuliangxiu?style=social"></a><br>
+<iframe src="https://ghbtns.com/github-btn.html?user=yuliangxiu&repo=ECON&type=star&count=true&v=2&size=small" frameborder="0" scrolling="0" width="100" height="20"></iframe>
+</th>
+<th width="40%">
+<iframe width="560" height="315" src="https://www.youtube.com/embed/5PEd_p90kS0" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
+</th>
+<th width="40%">
+<iframe width="560" height="315" src="https://www.youtube.com/embed/sbWZbTf6ZYk" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>
+</th>
+</table>
+'''
+
 from controlnet_aux import OpenposeDetector
 from diffusers import StableDiffusionControlNetPipeline, ControlNetModel
 from diffusers import UniPCMultistepScheduler
@@ -127,9 +134,6 @@ async (image_in_img, prompt, image_file_live_opt, live_conditioning) => {
 """
 
 # Constants
-low_threshold = 100
-high_threshold = 200
-default_step = 50
 cached = False
 
 # Models
@@ -167,11 +171,12 @@ blender, oc renderer, ultra high definition, 3d rendering
 def get_pose(image):
     return pose_model(image)
 
+import sys
 
-# def generate_texture(input_shape, text, seed, guidance_scale):
-#     iface = gr.Interface.load("spaces/TEXTurePaper/TEXTure")
-#     output_shape = iface(input_shape, text, seed, guidance_scale)
-#     return output_shape
+def read_logs():
+    sys.stdout.flush()
+    with open("output.log", "r") as f:
+        return f.read()
 
 
 def generate_images(image, prompt, image_file_live_opt='file', live_conditioning=None):
@@ -189,7 +194,7 @@ def generate_images(image, prompt, image_file_live_opt='file', live_conditioning
             pose,
             generator=generator,
             num_images_per_prompt=3,
-            num_inference_steps=20,
+            num_inference_steps=50,
         )
         all_outputs = []
         all_outputs.append(pose)
@@ -207,11 +212,17 @@ def toggle(choice):
         return gr.update(visible=False, value=None), gr.update(visible=True, value=canvas_html)
 
 
-examples_pose = glob.glob('examples/pose/*')
-examples_cloth = glob.glob('examples/cloth/*')
+examples_pose = 'examples/pose'
+examples_cloth = 'examples/cloth'
+
+def show_video():
+    return gr.update(visible=True), gr.update(visible=True)
 
 with gr.Blocks() as demo:
-    gr.Markdown(description)
+    
+    gr.Markdown(title)
+    gr.HTML(description)
+    gr.Markdown(bottom)
 
     out_lst = []
     with gr.Row():
@@ -227,7 +238,7 @@ with gr.Blocks() as demo:
 
                     with gr.Row():
                         image_in_img = gr.Image(
-                            source="upload", visible=True, type="pil", label="Image for Pose"
+                            visible=True, type="pil", label="Image for Pose"
                         )
                         canvas = gr.HTML(None, elem_id="canvas_html", visible=False)
 
@@ -246,7 +257,7 @@ with gr.Blocks() as demo:
                     gr.Markdown(hint_prompts)
 
                 with gr.Column():
-                    gallery = gr.Gallery(label="Generated Images").style(grid=[2], height="auto")
+                    gallery = gr.Gallery(label="Generated Images", columns=[2],rows=[2])
                     gallery_cache = gr.State()
 
                     gr.Markdown(
@@ -259,12 +270,12 @@ with gr.Blocks() as demo:
                     )
 
                     inp = gr.Image(type="filepath", label="Input Image for Reconstruction")
-                    fitting_step = gr.inputs.Slider(
+                    fitting_step = gr.Slider(
                         10,
                         100,
                         step=10,
                         label='Fitting steps (Slower yet Better-aligned SMPL-X)',
-                        default=default_step
+                        value=50
                     )
 
             with gr.Row():
@@ -275,7 +286,7 @@ with gr.Blocks() as demo:
                 fn=generate_images,
                 inputs=[image_in_img, prompt, image_file_live_opt, live_conditioning],
                 outputs=[gallery, gallery_cache],
-                _js=get_js_image
+                js=get_js_image
             )
 
             def get_select_index(cache, evt: gr.SelectData):
@@ -288,40 +299,41 @@ with gr.Blocks() as demo:
             )
 
             with gr.Row():
-
+                
                 gr.Examples(
-                    examples=list(examples_pose),
+                    examples=examples_pose,
                     inputs=[inp],
                     cache_examples=cached,
-                    fn=None,
-                    outputs=None,
+                    fn=generate_model,
+                    outputs=out_lst,
                     label="Hard Pose Examples"
                 )
 
                 gr.Examples(
-                    examples=list(examples_cloth),
+                    examples=examples_cloth,
                     inputs=[inp],
                     cache_examples=cached,
-                    fn=None,
-                    outputs=None,
+                    fn=generate_model,
+                    outputs=out_lst,
                     label="Loose Cloth Examples"
                 )
 
-            out_vid = gr.Video(label="Shared on Twitter with #ECON")
 
         with gr.Column():
-            overlap_inp = gr.Image(type="filepath", label="Image Normal Overlap").style(height=400)
+            overlap_inp = gr.Image(type="filepath", label="Image Normal Overlap")
             out_final = gr.Model3D(
                 clear_color=[0.0, 0.0, 0.0, 0.0], label="Clothed human", elem_id="avatar"
             )
             out_smpl = gr.Model3D(
-                clear_color=[0.0, 0.0, 0.0, 0.0], label="SMPL-X body", elem_id="avatar"
+                clear_color=[0.0, 0.0, 0.0, 0.0], label="SMPL-X body (via PIXIE)", elem_id="avatar"
             )
 
             vis_tensor_path = gr.State()
+            
 
-            with gr.Row():
-                btn_video = gr.Button("Generate Video (~3min)")
+            # logs = gr.Textbox(max_lines=10, label="Logs")
+            btn_video = gr.Button("Generate Video (~3min)", visible=False)
+            out_vid = gr.Video(label="Shared on Twitter with #ECON", visible=False)
 
     out_lst = [out_smpl, out_final, overlap_inp, vis_tensor_path]
 
@@ -332,10 +344,12 @@ with gr.Blocks() as demo:
     )
 
     btn_submit.click(fn=generate_model, inputs=[inp, fitting_step], outputs=out_lst)
-
-    demo.load(None, None, None, _js=load_js)
+    btn_submit.click(fn=show_video, outputs=[btn_video, out_vid])
+    # demo.load(read_logs, None, logs, every=1, queue=True, scroll_to_output=True)
+    demo.load(None, None, None, js=load_js)
 
 if __name__ == "__main__":
 
     demo.queue()
-    demo.launch(max_threads=1)
+    demo.launch(max_threads=4)
+    # demo.launch(max_threads=2, debug=True, server_port=8888, server_name="0.0.0.0")

apps/benchmark.py

@@ -90,7 +90,7 @@ if __name__ == "__main__":
     normal_net.netG.eval()
     print(
         colored(
-            f"Resume Normal Estimator from {Format.start} {cfg.normal_path} {Format.end}", "green"
+            f"Resume Normal Estimator from: {cfg.normal_path}", "green"
         )
     )
 

apps/infer.py

@@ -30,7 +30,7 @@ import trimesh
 from pytorch3d.ops import SubdivideMeshes
 from huggingface_hub import hf_hub_download
 from termcolor import colored
-from tqdm.auto import tqdm
+from tqdm import tqdm
 
 from apps.IFGeo import IFGeo
 from apps.Normal import Normal
@@ -65,14 +65,32 @@ def generate_video(vis_tensor_path):
 
     render.load_meshes(verts_lst, faces_lst)
     render.get_rendered_video_multi(in_tensor, tmp_path)
-
+    
     os.system(f"ffmpeg -y -loglevel quiet -stats -i {tmp_path} -vcodec libx264 {out_path}")
-
+    
     return out_path
 
-
+import sys
+class Logger:
+    def __init__(self, filename):
+        self.terminal = sys.stdout
+        self.log = open(filename, "w")
+
+    def write(self, message):
+        self.terminal.write(message)
+        self.log.write(message)
+        
+    def flush(self):
+        self.terminal.flush()
+        self.log.flush()
+        
+    def isatty(self):
+        return False  
+    
 def generate_model(in_path, fitting_step=50):
-
+    
+    sys.stdout = Logger("./output.log")
+    
     out_dir = "./results"
 
     # cfg read and merge
@@ -101,7 +119,7 @@ def generate_model(in_path, fitting_step=50):
     normal_net.netG.eval()
     print(
         colored(
-            f"Resume Normal Estimator from {Format.start} {cfg.normal_path} {Format.end}", "green"
+            f"Resume Normal Estimator from : {cfg.normal_path} ", "green"
         )
     )
 
@@ -129,10 +147,10 @@ def generate_model(in_path, fitting_step=50):
         ifnet = ifnet.to(device)
         ifnet.netG.eval()
 
-        print(colored(f"Resume IF-Net+ from {Format.start} {cfg.ifnet_path} {Format.end}", "green"))
-        print(colored(f"Complete with {Format.start} IF-Nets+ (Implicit) {Format.end}", "green"))
+        print(colored(f"Resume IF-Net+ from : {cfg.ifnet_path} ", "green"))
+        print(colored(f"Complete with : IF-Nets+ (Implicit) ", "green"))
     else:
-        print(colored(f"Complete with {Format.start} SMPL-X (Explicit) {Format.end}", "green"))
+        print(colored(f"Complete with : SMPL-X (Explicit) ", "green"))
 
     dataset = TestDataset(dataset_param, device)
 
@@ -142,7 +160,7 @@ def generate_model(in_path, fitting_step=50):
 
     losses = init_loss()
 
-    print(f"{data['name']}")
+    print(f"Subject name: {data['name']}")
 
     # final results rendered as image (PNG)
     # 1. Render the final fitted SMPL (xxx_smpl.png)
@@ -261,7 +279,8 @@ def generate_model(in_path, fitting_step=50):
 
             ghum_lmks = data["landmark"][:, SMPLX_object.ghum_smpl_pairs[:, 0], :2].to(device)
             ghum_conf = data["landmark"][:, SMPLX_object.ghum_smpl_pairs[:, 0], -1].to(device)
-            smpl_lmks = smpl_joints_3d[:, SMPLX_object.ghum_smpl_pairs[:, 1], :2]
+            smpl_lmks = smpl_joints_3d[:, SMPLX_object.ghum_smpl_pairs[:, 1], :2].to(device)
+
 
             # render optimized mesh as normal [-1,1]
             in_tensor["T_normal_F"], in_tensor["T_normal_B"] = dataset.render_normal(
@@ -293,7 +312,7 @@ def generate_model(in_path, fitting_step=50):
             # for highly occluded body, reply only on high-confidence landmarks, no silhouette+normal loss
 
             # BUG: PyTorch3D silhouette renderer generates dilated mask
-            bg_value = in_tensor["T_normal_F"][0, 0, 0, 0]
+            bg_value = in_tensor["T_normal_F"][0, 0, 0, 0].to(device)
             smpl_arr_fake = torch.cat([
                 in_tensor["T_normal_F"][:, 0].ne(bg_value).float(),
                 in_tensor["T_normal_B"][:, 0].ne(bg_value).float()
@@ -329,6 +348,7 @@ def generate_model(in_path, fitting_step=50):
             occlude_str = ''.join([str(j) for j in body_overlap_flag.int().tolist()])
             pbar_desc += colored(f"| loose:{loose_str}, occluded:{occlude_str}", "yellow")
             loop_smpl.set_description(pbar_desc)
+            print(pbar_desc)
 
             # save intermediate results
             if (i == fitting_step - 1):
@@ -611,7 +631,7 @@ def generate_model(in_path, fitting_step=50):
             cfg.bni.poisson_depth,
         )
         print(
-            colored(f"\n Poisson completion to {Format.start} {final_path} {Format.end}", "yellow")
+            colored(f"Poisson completion to : {final_path} ", "yellow")
         )
 
         dataset.render.load_meshes(final_mesh.vertices, final_mesh.faces)

gradio_cached_examples/13/log.csv

@@ -1,2 +0,0 @@
-flag,username,timestamp
-,,2023-04-15 18:15:46.412679

gradio_cached_examples/25/log.csv

@@ -1,6 +0,0 @@
-flag,username,timestamp
-,,2023-04-16 10:48:00.715491
-,,2023-04-16 10:50:02.250539
-,,2023-04-16 10:52:15.683112
-,,2023-04-16 10:54:18.253116
-,,2023-04-16 10:56:22.892765

lib/common/imutils.py

@@ -193,7 +193,7 @@ def process_image(img_file, hps_type, single, input_res, detector):
     predictions = detector(img_square / 255.)[0]
 
     if single:
-        top_score = predictions["scores"][predictions["labels"] == 1].max()
+        top_score = max(predictions["scores"][predictions["labels"] == 1])
         human_ids = torch.where(predictions["scores"] == top_score)[0]
     else:
         human_ids = torch.logical_and(predictions["labels"] == 1,

lib/common/local_affine.py

@@ -138,6 +138,8 @@ def register(target_mesh, src_mesh, device, verbose=True):
         cloth_loss.backward(retain_graph=True)
         optimizer_cloth.step()
         scheduler_cloth.step(cloth_loss)
+        
+        print(pbar_desc)
 
     final = trimesh.Trimesh(
         src_mesh.verts_packed().detach().squeeze(0).cpu(),

lib/common/render.py

@@ -16,6 +16,7 @@
 
 import math
 import os
+import sys
 
 import cv2
 import numpy as np
@@ -318,7 +319,7 @@ class Render:
         )
 
         pbar = tqdm(range(len(self.meshes)))
-        pbar.set_description(colored(f"Normal Rendering {os.path.basename(save_path)}...", "blue"))
+        print(colored(f"Normal Rendering {os.path.basename(save_path)}...", "blue"))
 
         mesh_renders = []    #[(N_cam, 3, res, res)*N_mesh]
 
@@ -343,10 +344,10 @@ class Render:
                                  )[..., :3].permute(0, 3, 1, 2)
                 )
             mesh_renders.append(torch.cat(norm_lst).detach().cpu())
-
+            
         # generate video frame by frame
         pbar = tqdm(range(len(self.cam_pos["around"])))
-        pbar.set_description(colored(f"Video Exporting {os.path.basename(save_path)}...", "blue"))
+        print(colored(f"Video Exporting {os.path.basename(save_path)}...", "blue"))
 
         for cam_id in pbar:
             img_raw = data["img_raw"]

lib/dataset/TestDataset.py

@@ -81,7 +81,7 @@ class TestDataset:
 
         print(
             colored(
-                f"SMPL-X estimate with {Format.start} {self.hps_type.upper()} {Format.end}", "green"
+                f"SMPL-X estimate with {self.hps_type.upper()}", "green"
             )
         )
 

lib/pymafx/utils/sample_mesh.py

@@ -1,66 +0,0 @@
-import os
-
-import numpy as np
-import trimesh
-
-from .utils.libmesh import check_mesh_contains
-
-
-def get_occ_gt(
-    in_path=None,
-    vertices=None,
-    faces=None,
-    pts_num=1000,
-    points_sigma=0.01,
-    with_dp=False,
-    points=None,
-    extra_points=None
-):
-    if in_path is not None:
-        mesh = trimesh.load(in_path, process=False)
-        print(type(mesh.vertices), mesh.vertices.shape, mesh.faces.shape)
-
-    mesh = trimesh.Trimesh(vertices=vertices, faces=faces, process=False)
-
-    # print('get_occ_gt', type(mesh.vertices), mesh.vertices.shape, mesh.faces.shape)
-
-    # points_size = 100000
-    points_padding = 0.1
-    # points_sigma = 0.01
-    points_uniform_ratio = 0.5
-    n_points_uniform = int(pts_num * points_uniform_ratio)
-    n_points_surface = pts_num - n_points_uniform
-
-    if points is None:
-        points_scale = 2.0
-        boxsize = points_scale + points_padding
-        points_uniform = np.random.rand(n_points_uniform, 3)
-        points_uniform = boxsize * (points_uniform - 0.5)
-        points_surface, index_surface = mesh.sample(n_points_surface, return_index=True)
-        points_surface += points_sigma * np.random.randn(n_points_surface, 3)
-        points = np.concatenate([points_uniform, points_surface], axis=0)
-
-    if extra_points is not None:
-        extra_points += points_sigma * np.random.randn(len(extra_points), 3)
-        points = np.concatenate([points, extra_points], axis=0)
-
-    occupancies = check_mesh_contains(mesh, points)
-
-    index_surface = None
-
-    # points = points.astype(dtype)
-
-    # print('occupancies', occupancies.dtype, np.sum(occupancies), occupancies.shape)
-    # occupancies = np.packbits(occupancies)
-    # print('occupancies bit', occupancies.dtype, np.sum(occupancies), occupancies.shape)
-
-    # print('occupancies', points.shape, occupancies.shape, occupancies.dtype, np.sum(occupancies), index_surface.shape)
-
-    return_dict = {}
-    return_dict['points'] = points
-    return_dict['points.occ'] = occupancies
-    return_dict['sf_sidx'] = index_surface
-
-    # export_pointcloud(mesh, modelname, loc, scale, args)
-    # export_points(mesh, modelname, loc, scale, args)
-    return return_dict

output.log

@@ -0,0 +1 @@
+

requirements.txt

@@ -27,6 +27,6 @@ transformers
 controlnet_aux
 xformers==0.0.16
 triton
+diffusers
+accelerate
 git+https://github.com/YuliangXiu/rembg.git
-git+https://github.com/huggingface/diffusers.git
-git+https://github.com/huggingface/accelerate.git