minify, update requirements

README.md

@@ -17,12 +17,21 @@ This project can be used from other projects as follows.
 import torch
 from diffusers import DiffusionPipeline
 
-pipeline = DiffusionPipeline.from_pretrained(
+# Text to Multi-View Diffusion
+text_pipeline = DiffusionPipeline.from_pretrained(
     "ashawkey/mvdream-sd2.1-diffusers",
     custom_pipeline="dylanebert/multi_view_diffusion",
     torch_dtype=torch.float16,
     trust_remote_code=True,
-)
+).to("cuda")
+
+# Image to Multi-View Diffusion
+image_pipeline = DiffusionPipeline.from_pretrained(
+    "ashawkey/imagedream-ipmv-diffusers",
+    custom_pipeline="dylanebert/multi_view_diffusion",
+    torch_dtype=torch.float16,
+    trust_remote_code=True,
+).to("cuda")
 ```
 
 Original model card below.

requirements.txt

@@ -0,0 +1,55 @@
+accelerate==0.28.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+diffusers==0.27.2
+einops==0.7.0
+executing==2.0.1
+filelock==3.13.3
+fsspec==2024.3.1
+huggingface-hub==0.22.2
+idna==3.6
+importlib_metadata==7.1.0
+Jinja2==3.1.3
+kiui==0.2.7
+lazy_loader==0.3
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.2.1
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.4.99
+nvidia-nvtx-cu12==12.1.105
+objprint==0.2.3
+opencv-python==4.9.0.80
+packaging==24.0
+pillow==10.2.0
+psutil==5.9.8
+Pygments==2.17.2
+PyYAML==6.0.1
+regex==2023.12.25
+requests==2.31.0
+rich==13.7.1
+safetensors==0.4.2
+scipy==1.12.0
+sympy==1.12
+tokenizers==0.15.2
+torch==2.2.2
+tqdm==4.66.2
+transformers==4.39.2
+triton==2.2.0
+typing_extensions==4.10.0
+urllib3==2.2.1
+varname==0.13.0
+xformers==0.0.25.post1
+zipp==3.18.1

run_imagedream.py

@@ -1,32 +0,0 @@
-import torch
-import kiui
-import numpy as np
-import argparse
-from pipeline import MVDreamPipeline
-
-pipe = MVDreamPipeline.from_pretrained(
-    # "./weights_imagedream", # local weights
-    "ashawkey/imagedream-ipmv-diffusers", # remote weights
-    torch_dtype=torch.float16,
-    trust_remote_code=True,
-)
-pipe = pipe.to("cuda")
-
-
-parser = argparse.ArgumentParser(description="ImageDream")
-parser.add_argument("image", type=str, default='data/anya_rgba.png')
-parser.add_argument("--prompt", type=str, default="")
-args = parser.parse_args()
-
-for i in range(5):
-    input_image = kiui.read_image(args.image, mode='float')
-    image = pipe(args.prompt, input_image, guidance_scale=5, num_inference_steps=30, elevation=0)
-    grid = np.concatenate(
-        [
-            np.concatenate([image[0], image[2]], axis=0),
-            np.concatenate([image[1], image[3]], axis=0),
-        ],
-        axis=1,
-    )
-    # kiui.vis.plot_image(grid)
-    kiui.write_image(f'test_imagedream_{i}.jpg', grid)

run_mvdream.py

@@ -1,31 +0,0 @@
-import torch
-import kiui
-import numpy as np
-import argparse
-from pipeline import MVDreamPipeline
-
-pipe = MVDreamPipeline.from_pretrained(
-    # "./weights_mvdream", # local weights
-    'ashawkey/mvdream-sd2.1-diffusers', # remote weights
-    torch_dtype=torch.float16,
-    trust_remote_code=True,
-)
-
-pipe = pipe.to("cuda")
-
-
-parser = argparse.ArgumentParser(description="MVDream")
-parser.add_argument("prompt", type=str, default="a cute owl 3d model")
-args = parser.parse_args()
-
-for i in range(5):
-    image = pipe(args.prompt, guidance_scale=5, num_inference_steps=30, elevation=0)
-    grid = np.concatenate(
-        [
-            np.concatenate([image[0], image[2]], axis=0),
-            np.concatenate([image[1], image[3]], axis=0),
-        ],
-        axis=1,
-    )
-    # kiui.vis.plot_image(grid)
-    kiui.write_image(f'test_mvdream_{i}.jpg', grid)