FIx

README.md

@@ -5,11 +5,11 @@ colorFrom: red
 colorTo: purple
 sdk: gradio
 python_version: 3.10.8
-sdk_version: 4.12.0
+sdk_version: 5.15.0
 app_file: app.py
 pinned: true
 short_description: Create a 1M faces 3D colored model from an image!
 license: mit
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,22 +1,25 @@
 import shlex
 import subprocess
+
+
+subprocess.run(shlex.split("pip install pip==24.0"), check=True)
 subprocess.run(
     shlex.split(
         "pip install package/onnxruntime_gpu-1.17.0-cp310-cp310-manylinux_2_28_x86_64.whl --force-reinstall --no-deps"
-    )
+    ), check=True
 )
 subprocess.run(
     shlex.split(
         "pip install package/nvdiffrast-0.3.1.torch-cp310-cp310-linux_x86_64.whl --force-reinstall --no-deps"
-    )
+    ), check=True
 )
 
+
 if __name__ == "__main__":
-    import os
-    from huggingface_hub import login
-    hf_token = os.environ.get("HF_TOKEN")
-    login(token=hf_token)
-    
+    from huggingface_hub import snapshot_download
+
+    snapshot_download("Wuvin/Unique3D", repo_type="model", local_dir="./ckpt")
+
     import os
     import sys
     sys.path.append(os.curdir)
@@ -51,7 +54,7 @@ _DESCRIPTION = '''
 
 def launch():
     model_zoo.init_models()
-        
+
     with gr.Blocks(
         title=_TITLE,
         # theme=gr.themes.Monochrome(),
@@ -63,6 +66,6 @@ def launch():
         create_3d_ui("wkl")
 
     demo.queue().launch(share=True)
-    
+
 if __name__ == '__main__':
     fire.Fire(launch)

ckpt/controlnet-tile/config.json

@@ -1,52 +0,0 @@
-{
-  "_class_name": "ControlNetModel",
-  "_diffusers_version": "0.27.2",
-  "_name_or_path": "lllyasviel/control_v11f1e_sd15_tile",
-  "act_fn": "silu",
-  "addition_embed_type": null,
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
-  "attention_head_dim": 8,
-  "block_out_channels": [
-    320,
-    640,
-    1280,
-    1280
-  ],
-  "class_embed_type": null,
-  "conditioning_channels": 3,
-  "conditioning_embedding_out_channels": [
-    16,
-    32,
-    96,
-    256
-  ],
-  "controlnet_conditioning_channel_order": "rgb",
-  "cross_attention_dim": 768,
-  "down_block_types": [
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "DownBlock2D"
-  ],
-  "downsample_padding": 1,
-  "encoder_hid_dim": null,
-  "encoder_hid_dim_type": null,
-  "flip_sin_to_cos": true,
-  "freq_shift": 0,
-  "global_pool_conditions": false,
-  "in_channels": 4,
-  "layers_per_block": 2,
-  "mid_block_scale_factor": 1,
-  "mid_block_type": "UNetMidBlock2DCrossAttn",
-  "norm_eps": 1e-05,
-  "norm_num_groups": 32,
-  "num_attention_heads": null,
-  "num_class_embeds": null,
-  "only_cross_attention": false,
-  "projection_class_embeddings_input_dim": null,
-  "resnet_time_scale_shift": "default",
-  "transformer_layers_per_block": 1,
-  "upcast_attention": false,
-  "use_linear_projection": false
-}

ckpt/controlnet-tile/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:845d3845053912728cd1453029a0ef87d3c0a3082a083ba393f36eaa5fb0e218
-size 1445157120

ckpt/image2normal/feature_extractor/preprocessor_config.json

@@ -1,44 +0,0 @@
-{
-  "_valid_processor_keys": [
-    "images",
-    "do_resize",
-    "size",
-    "resample",
-    "do_center_crop",
-    "crop_size",
-    "do_rescale",
-    "rescale_factor",
-    "do_normalize",
-    "image_mean",
-    "image_std",
-    "do_convert_rgb",
-    "return_tensors",
-    "data_format",
-    "input_data_format"
-  ],
-  "crop_size": {
-    "height": 224,
-    "width": 224
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
-  ],
-  "image_processor_type": "CLIPImageProcessor",
-  "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
-  ],
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 224
-  }
-}

ckpt/image2normal/image_encoder/config.json

@@ -1,23 +0,0 @@
-{
-  "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
-  "architectures": [
-    "CLIPVisionModelWithProjection"
-  ],
-  "attention_dropout": 0.0,
-  "dropout": 0.0,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 1024,
-  "image_size": 224,
-  "initializer_factor": 1.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "model_type": "clip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 24,
-  "patch_size": 14,
-  "projection_dim": 768,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3"
-}

ckpt/image2normal/image_encoder/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e4b33d864f89a793357a768cb07d0dc18d6a14e6664f4110a0d535ca9ba78da8
-size 607980488

ckpt/image2normal/model_index.json

@@ -1,31 +0,0 @@
-{
-  "_class_name": "StableDiffusionImageCustomPipeline",
-  "_diffusers_version": "0.27.2",
-  "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
-  "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
-  ],
-  "image_encoder": [
-    "transformers",
-    "CLIPVisionModelWithProjection"
-  ],
-  "noisy_cond_latents": false,
-  "requires_safety_checker": true,
-  "safety_checker": [
-    null,
-    null
-  ],
-  "scheduler": [
-    "diffusers",
-    "EulerAncestralDiscreteScheduler"
-  ],
-  "unet": [
-    "diffusers",
-    "UNet2DConditionModel"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKL"
-  ]
-}

ckpt/image2normal/scheduler/scheduler_config.json

@@ -1,16 +0,0 @@
-{
-  "_class_name": "EulerAncestralDiscreteScheduler",
-  "_diffusers_version": "0.27.2",
-  "beta_end": 0.012,
-  "beta_schedule": "scaled_linear",
-  "beta_start": 0.00085,
-  "clip_sample": false,
-  "num_train_timesteps": 1000,
-  "prediction_type": "epsilon",
-  "rescale_betas_zero_snr": false,
-  "set_alpha_to_one": false,
-  "skip_prk_steps": true,
-  "steps_offset": 1,
-  "timestep_spacing": "linspace",
-  "trained_betas": null
-}

ckpt/image2normal/unet/config.json

@@ -1,68 +0,0 @@
-{
-  "_class_name": "UnifieldWrappedUNet",
-  "_diffusers_version": "0.27.2",
-  "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
-  "act_fn": "silu",
-  "addition_embed_type": null,
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
-  "attention_head_dim": 8,
-  "attention_type": "default",
-  "block_out_channels": [
-    320,
-    640,
-    1280,
-    1280
-  ],
-  "center_input_sample": false,
-  "class_embed_type": null,
-  "class_embeddings_concat": false,
-  "conv_in_kernel": 3,
-  "conv_out_kernel": 3,
-  "cross_attention_dim": 768,
-  "cross_attention_norm": null,
-  "down_block_types": [
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "DownBlock2D"
-  ],
-  "downsample_padding": 1,
-  "dropout": 0.0,
-  "dual_cross_attention": false,
-  "encoder_hid_dim": null,
-  "encoder_hid_dim_type": null,
-  "flip_sin_to_cos": true,
-  "freq_shift": 0,
-  "in_channels": 4,
-  "layers_per_block": 2,
-  "mid_block_only_cross_attention": null,
-  "mid_block_scale_factor": 1,
-  "mid_block_type": "UNetMidBlock2DCrossAttn",
-  "norm_eps": 1e-05,
-  "norm_num_groups": 32,
-  "num_attention_heads": null,
-  "num_class_embeds": null,
-  "only_cross_attention": false,
-  "out_channels": 4,
-  "projection_class_embeddings_input_dim": null,
-  "resnet_out_scale_factor": 1.0,
-  "resnet_skip_time_act": false,
-  "resnet_time_scale_shift": "default",
-  "reverse_transformer_layers_per_block": null,
-  "sample_size": 64,
-  "time_cond_proj_dim": null,
-  "time_embedding_act_fn": null,
-  "time_embedding_dim": null,
-  "time_embedding_type": "positional",
-  "timestep_post_act": null,
-  "transformer_layers_per_block": 1,
-  "up_block_types": [
-    "UpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D"
-  ],
-  "upcast_attention": false,
-  "use_linear_projection": false
-}

ckpt/image2normal/unet/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f5cbaf1d56619345ce78de8cfbb20d94923b3305a364bf6a5b2a2cc422d4b701
-size 3537503456

ckpt/image2normal/unet_state_dict.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8df80d09e953d338aa6d8decd0351c5045f52ec6e2645eee2027ccb8792c8ed8
-size 3537964654

ckpt/image2normal/vae/config.json

@@ -1,34 +0,0 @@
-{
-  "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.27.2",
-  "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
-  "act_fn": "silu",
-  "block_out_channels": [
-    128,
-    256,
-    512,
-    512
-  ],
-  "down_block_types": [
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D"
-  ],
-  "force_upcast": true,
-  "in_channels": 3,
-  "latent_channels": 4,
-  "latents_mean": null,
-  "latents_std": null,
-  "layers_per_block": 2,
-  "norm_num_groups": 32,
-  "out_channels": 3,
-  "sample_size": 256,
-  "scaling_factor": 0.18215,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ]
-}

ckpt/image2normal/vae/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8d0c34f57abe50f323040f2366c8e22b941068dcdf53c8eb1d6fafb838afecb7
-size 167335590

ckpt/img2mvimg/feature_extractor/preprocessor_config.json

@@ -1,44 +0,0 @@
-{
-  "_valid_processor_keys": [
-    "images",
-    "do_resize",
-    "size",
-    "resample",
-    "do_center_crop",
-    "crop_size",
-    "do_rescale",
-    "rescale_factor",
-    "do_normalize",
-    "image_mean",
-    "image_std",
-    "do_convert_rgb",
-    "return_tensors",
-    "data_format",
-    "input_data_format"
-  ],
-  "crop_size": {
-    "height": 224,
-    "width": 224
-  },
-  "do_center_crop": true,
-  "do_convert_rgb": true,
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.48145466,
-    0.4578275,
-    0.40821073
-  ],
-  "image_processor_type": "CLIPImageProcessor",
-  "image_std": [
-    0.26862954,
-    0.26130258,
-    0.27577711
-  ],
-  "resample": 3,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "shortest_edge": 224
-  }
-}

ckpt/img2mvimg/image_encoder/config.json

@@ -1,23 +0,0 @@
-{
-  "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
-  "architectures": [
-    "CLIPVisionModelWithProjection"
-  ],
-  "attention_dropout": 0.0,
-  "dropout": 0.0,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 1024,
-  "image_size": 224,
-  "initializer_factor": 1.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "model_type": "clip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 24,
-  "patch_size": 14,
-  "projection_dim": 768,
-  "torch_dtype": "float32",
-  "transformers_version": "4.39.3"
-}

ckpt/img2mvimg/image_encoder/model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:77b33d2a3a643650857672e880ccf73adbaf114fbbadec36d142ee9d48af7e20
-size 1215912728

ckpt/img2mvimg/model_index.json

@@ -1,31 +0,0 @@
-{
-  "_class_name": "StableDiffusionImage2MVCustomPipeline",
-  "_diffusers_version": "0.27.2",
-  "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
-  "condition_offset": true,
-  "feature_extractor": [
-    "transformers",
-    "CLIPImageProcessor"
-  ],
-  "image_encoder": [
-    "transformers",
-    "CLIPVisionModelWithProjection"
-  ],
-  "requires_safety_checker": true,
-  "safety_checker": [
-    null,
-    null
-  ],
-  "scheduler": [
-    "diffusers",
-    "DDIMScheduler"
-  ],
-  "unet": [
-    "diffusers",
-    "UNet2DConditionModel"
-  ],
-  "vae": [
-    "diffusers",
-    "AutoencoderKL"
-  ]
-}

ckpt/img2mvimg/scheduler/scheduler_config.json

@@ -1,20 +0,0 @@
-{
-  "_class_name": "DDIMScheduler",
-  "_diffusers_version": "0.27.2",
-  "beta_end": 0.012,
-  "beta_schedule": "scaled_linear",
-  "beta_start": 0.00085,
-  "clip_sample": false,
-  "clip_sample_range": 1.0,
-  "dynamic_thresholding_ratio": 0.995,
-  "num_train_timesteps": 1000,
-  "prediction_type": "epsilon",
-  "rescale_betas_zero_snr": false,
-  "sample_max_value": 1.0,
-  "set_alpha_to_one": false,
-  "skip_prk_steps": true,
-  "steps_offset": 1,
-  "thresholding": false,
-  "timestep_spacing": "leading",
-  "trained_betas": null
-}

ckpt/img2mvimg/unet/config.json

@@ -1,68 +0,0 @@
-{
-  "_class_name": "UnifieldWrappedUNet",
-  "_diffusers_version": "0.27.2",
-  "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
-  "act_fn": "silu",
-  "addition_embed_type": null,
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": null,
-  "attention_head_dim": 8,
-  "attention_type": "default",
-  "block_out_channels": [
-    320,
-    640,
-    1280,
-    1280
-  ],
-  "center_input_sample": false,
-  "class_embed_type": null,
-  "class_embeddings_concat": false,
-  "conv_in_kernel": 3,
-  "conv_out_kernel": 3,
-  "cross_attention_dim": 768,
-  "cross_attention_norm": null,
-  "down_block_types": [
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D",
-    "DownBlock2D"
-  ],
-  "downsample_padding": 1,
-  "dropout": 0.0,
-  "dual_cross_attention": false,
-  "encoder_hid_dim": null,
-  "encoder_hid_dim_type": null,
-  "flip_sin_to_cos": true,
-  "freq_shift": 0,
-  "in_channels": 8,
-  "layers_per_block": 2,
-  "mid_block_only_cross_attention": null,
-  "mid_block_scale_factor": 1,
-  "mid_block_type": "UNetMidBlock2DCrossAttn",
-  "norm_eps": 1e-05,
-  "norm_num_groups": 32,
-  "num_attention_heads": null,
-  "num_class_embeds": 8,
-  "only_cross_attention": false,
-  "out_channels": 4,
-  "projection_class_embeddings_input_dim": null,
-  "resnet_out_scale_factor": 1.0,
-  "resnet_skip_time_act": false,
-  "resnet_time_scale_shift": "default",
-  "reverse_transformer_layers_per_block": null,
-  "sample_size": 64,
-  "time_cond_proj_dim": null,
-  "time_embedding_act_fn": null,
-  "time_embedding_dim": null,
-  "time_embedding_type": "positional",
-  "timestep_post_act": null,
-  "transformer_layers_per_block": 1,
-  "up_block_types": [
-    "UpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D",
-    "CrossAttnUpBlock2D"
-  ],
-  "upcast_attention": false,
-  "use_linear_projection": false
-}

ckpt/img2mvimg/unet/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:93a3b4e678efac0c997e76df465df13136a4b0f1732e534a1200fad9e04cd0f9
-size 3438254688

ckpt/img2mvimg/unet_state_dict.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0dff2fdba450af0e10c3a847ba66a530170be2e9b9c9f4c834483515e82738b5
-size 3438460972

ckpt/img2mvimg/vae/config.json

@@ -1,34 +0,0 @@
-{
-  "_class_name": "AutoencoderKL",
-  "_diffusers_version": "0.27.2",
-  "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
-  "act_fn": "silu",
-  "block_out_channels": [
-    128,
-    256,
-    512,
-    512
-  ],
-  "down_block_types": [
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D",
-    "DownEncoderBlock2D"
-  ],
-  "force_upcast": true,
-  "in_channels": 3,
-  "latent_channels": 4,
-  "latents_mean": null,
-  "latents_std": null,
-  "layers_per_block": 2,
-  "norm_num_groups": 32,
-  "out_channels": 3,
-  "sample_size": 256,
-  "scaling_factor": 0.18215,
-  "up_block_types": [
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D",
-    "UpDecoderBlock2D"
-  ]
-}

ckpt/img2mvimg/vae/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
-size 334643268

ckpt/realesrgan-x4.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9bc5d0c85207adad8bca26286f0c0007f266f85e7aa7c454c565da9b5f3c940a
-size 67051617

ckpt/v1-inference.yaml

@@ -1,70 +0,0 @@
-model:
-  base_learning_rate: 1.0e-04
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.00085
-    linear_end: 0.0120
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: "jpg"
-    cond_stage_key: "txt"
-    image_size: 64
-    channels: 4
-    cond_stage_trainable: false   # Note: different from the one we trained before
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False
-
-    scheduler_config: # 10000 warmup steps
-      target: ldm.lr_scheduler.LambdaLinearScheduler
-      params:
-        warm_up_steps: [ 10000 ]
-        cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
-        f_start: [ 1.e-6 ]
-        f_max: [ 1. ]
-        f_min: [ 1. ]
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        image_size: 32 # unused
-        in_channels: 4
-        out_channels: 4
-        model_channels: 320
-        attention_resolutions: [ 4, 2, 1 ]
-        num_res_blocks: 2
-        channel_mult: [ 1, 2, 4, 4 ]
-        num_heads: 8
-        use_spatial_transformer: True
-        transformer_depth: 1
-        context_dim: 768
-        use_checkpoint: True
-        legacy: False
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: val/rec_loss
-        ddconfig:
-          double_z: true
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenCLIPEmbedder

custum_3d_diffusion/custum_modules/unifield_processor.py

@@ -70,7 +70,7 @@ class AttnConfig:
     use_mv_joint_attn: bool = False
     
     # for unet
-    init_unet_path: str = "runwayml/stable-diffusion-v1-5"
+    init_unet_path: str = "stable-diffusion-v1-5/stable-diffusion-v1-5"
     init_num_cls_label: int = 0                         # for initialize
     cls_labels: List[int] = field(default_factory=lambda: [])
     cls_label_type: str = "embedding"

gradio_app/all_models.py

@@ -6,7 +6,7 @@ from diffusers import StableDiffusionControlNetImg2ImgPipeline, StableDiffusionP
 class MyModelZoo:
     _pipe_disney_controlnet_lineart_ipadapter_i2i: StableDiffusionControlNetImg2ImgPipeline = None
     
-    base_model = "benjamin-paine/stable-diffusion-v1-5"
+    base_model = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 
     def __init__(self, base_model=None) -> None:
         if base_model is not None:

requirements.txt

@@ -9,7 +9,7 @@ fire
 gradio
 jaxtyping
 numba
-numpy
+numpy<2
 omegaconf>=2.3.0
 opencv_python
 opencv_python_headless
@@ -18,7 +18,6 @@ Pillow
 pygltflib
 pymeshlab>=2023.12
 rembg[gpu]
-torch>=2.0.1
 torch_scatter @ https://data.pyg.org/whl/torch-2.2.0%2Bcu121/torch_scatter-2.1.2%2Bpt22cu121-cp310-cp310-linux_x86_64.whl
 tqdm
 transformers
@@ -26,4 +25,4 @@ trimesh
 typeguard
 wandb
 xformers
-ninja
+ninja

scripts/sd_model_zoo.py

@@ -4,7 +4,7 @@ import torch
 from copy import deepcopy
 
 ENABLE_CPU_CACHE = False
-DEFAULT_BASE_MODEL = "benjamin-paine/stable-diffusion-v1-5"
+DEFAULT_BASE_MODEL = "stable-diffusion-v1-5/stable-diffusion-v1-5"
 
 cached_models = {}  # cache for models to avoid repeated loading, key is model name
 def cache_model(func):