remove old models

README.md

@@ -28,10 +28,9 @@ a handsome man relaxing in a chair, shirt widely unbuttoned, eyes closed, close
 - [x] adaptive resize размеры
 - [x] пофиксить загрузку маски
 - [x] подобрать нормальные промпты к примерам, добавить negative prompt (https://blog.segmind.com/prompt-guide-for-stable-diffusion-xl-crafting-textual-descriptions-for-image-generation/)
-- [ ] сгенерировать прикольные примеры - штаны на голове и т д
 - [ ] разобраться с выставлением device в пайплайн
 - [ ] удалить ненужные веса
 - [ ] небольшой рефач - dark theme - можно попробовать
 - [ ] проверка ссылок
-- [ ] залить версию в main
+- [ ] залить версию в main  
 - [ ] настроить запуск в hugging space

config.py

@@ -17,7 +17,7 @@ class PipelineConfig:
 
     vae_path: str = 'madebyollin/sdxl-vae-fp16-fix'
 
-    controlnet_path: str = os.path.join(weights_path, 'controlnet_rgb')
+    controlnet_path: str = os.path.join(weights_path, 'controlnet')
 
     segmentation_model_path: str = os.path.join(weights_path, 'cloth_segm.pth')
 

weights/controlnet_adaptive/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5edfaac535c704da470ecf41614b3b84a4ead9d5f25f970de38ad026e25e5aa1
-size 5004167864

weights/controlnet_baseline/config.json

@@ -1,57 +0,0 @@
-{
-  "_class_name": "ControlNetModel",
-  "_diffusers_version": "0.25.0.dev0",
-  "act_fn": "silu",
-  "addition_embed_type": "text_time",
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": 256,
-  "attention_head_dim": [
-    5,
-    10,
-    20
-  ],
-  "block_out_channels": [
-    320,
-    640,
-    1280
-  ],
-  "class_embed_type": null,
-  "conditioning_channels": 3,
-  "conditioning_embedding_out_channels": [
-    16,
-    32,
-    96,
-    256
-  ],
-  "controlnet_conditioning_channel_order": "rgb",
-  "cross_attention_dim": 2048,
-  "down_block_types": [
-    "DownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D"
-  ],
-  "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": 2816,
-  "resnet_time_scale_shift": "default",
-  "transformer_layers_per_block": [
-    1,
-    2,
-    10
-  ],
-  "upcast_attention": null,
-  "use_linear_projection": true
-}

weights/controlnet_baseline/diffusion_pytorch_model.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f85f8ade2174d2757de3b00d302309d99e0b7995dc45f610ad9bf3d9aac95470
-size 5004167864

weights/controlnet_rgb/config.json

@@ -1,57 +0,0 @@
-{
-  "_class_name": "ControlNetModel",
-  "_diffusers_version": "0.25.0.dev0",
-  "act_fn": "silu",
-  "addition_embed_type": "text_time",
-  "addition_embed_type_num_heads": 64,
-  "addition_time_embed_dim": 256,
-  "attention_head_dim": [
-    5,
-    10,
-    20
-  ],
-  "block_out_channels": [
-    320,
-    640,
-    1280
-  ],
-  "class_embed_type": null,
-  "conditioning_channels": 3,
-  "conditioning_embedding_out_channels": [
-    16,
-    32,
-    96,
-    256
-  ],
-  "controlnet_conditioning_channel_order": "rgb",
-  "cross_attention_dim": 2048,
-  "down_block_types": [
-    "DownBlock2D",
-    "CrossAttnDownBlock2D",
-    "CrossAttnDownBlock2D"
-  ],
-  "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": 2816,
-  "resnet_time_scale_shift": "default",
-  "transformer_layers_per_block": [
-    1,
-    2,
-    10
-  ],
-  "upcast_attention": null,
-  "use_linear_projection": true
-}