Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .hfd/aria2c_urls.txt +0 -0
- .hfd/last_download_command +1 -0
- .hfd/repo_metadata.json +1 -0
- README.md +3 -0
- checkpoint/finetune/ade20k/config.json +52 -0
- checkpoint/finetune/ade20k/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/finetune/cocostuff/config.json +52 -0
- checkpoint/finetune/cocostuff/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/finetune/depth/config.json +52 -0
- checkpoint/finetune/depth/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/finetune/hed/config.json +52 -0
- checkpoint/finetune/hed/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/finetune/lineart/config.json +52 -0
- checkpoint/finetune/lineart/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/reward/ade20k/config.json +52 -0
- checkpoint/reward/ade20k/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/reward/cocostuff/config.json +52 -0
- checkpoint/reward/cocostuff/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/reward/depth/config.json +52 -0
- checkpoint/reward/depth/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/reward/hed/config.json +52 -0
- checkpoint/reward/hed/diffusion_pytorch_model.safetensors +3 -0
- checkpoint/reward/lineart/config.json +52 -0
- checkpoint/reward/lineart/diffusion_pytorch_model.safetensors +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
*.json filter=lfs diff=lfs merge=lfs -text
|
.hfd/aria2c_urls.txt
ADDED
|
File without changes
|
.hfd/last_download_command
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
REPO_ID=grenoble/Ctrl-u TOOL=aria2c INCLUDE_PATTERNS= EXCLUDE_PATTERNS= DATASET=0 HF_USERNAME= HF_TOKEN= HF_TOKEN=https://hf-mirror.com REVISION=main
|
.hfd/repo_metadata.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_id":"67a85fb62fbf63093ccf834a","id":"grenoble/Ctrl-u","private":false,"library_name":"diffusers","tags":["diffusers","safetensors","license:mit","region:us"],"downloads":0,"likes":0,"modelId":"grenoble/Ctrl-u","author":"grenoble","sha":"c97b19ca758e1b00e5358fec5f91ae92b994aca0","lastModified":"2025-02-19T05:13:01.000Z","gated":false,"disabled":false,"model-index":null,"cardData":{"license":"mit"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"checkpoint/finetune/ade20k/config.json"},{"rfilename":"checkpoint/finetune/ade20k/diffusion_pytorch_model.safetensors"},{"rfilename":"checkpoint/finetune/cocostuff/config.json"},{"rfilename":"checkpoint/finetune/cocostuff/diffusion_pytorch_model.safetensors"},{"rfilename":"checkpoint/finetune/depth/config.json"},{"rfilename":"checkpoint/finetune/depth/diffusion_pytorch_model.safetensors"},{"rfilename":"checkpoint/finetune/hed/config.json"},{"rfilename":"checkpoint/finetune/hed/diffusion_pytorch_model.safetensors"},{"rfilename":"checkpoint/finetune/lineart/config.json"},{"rfilename":"checkpoint/finetune/lineart/diffusion_pytorch_model.safetensors"},{"rfilename":"checkpoint/reward/ade20k/config.json"},{"rfilename":"checkpoint/reward/ade20k/diffusion_pytorch_model.safetensors"},{"rfilename":"checkpoint/reward/cocostuff/config.json"},{"rfilename":"checkpoint/reward/cocostuff/diffusion_pytorch_model.safetensors"},{"rfilename":"checkpoint/reward/depth/config.json"},{"rfilename":"checkpoint/reward/depth/diffusion_pytorch_model.safetensors"},{"rfilename":"checkpoint/reward/hed/config.json"},{"rfilename":"checkpoint/reward/hed/diffusion_pytorch_model.safetensors"},{"rfilename":"checkpoint/reward/lineart/config.json"},{"rfilename":"checkpoint/reward/lineart/diffusion_pytorch_model.safetensors"}],"spaces":[],"createdAt":"2025-02-09T07:56:38.000Z","usedStorage":14451583519}
|
README.md
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
checkpoint/finetune/ade20k/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"_name_or_path": "lllyasviel/control_v11p_sd15_seg",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"class_embed_type": null,
|
| 17 |
+
"conditioning_channels": 3,
|
| 18 |
+
"conditioning_embedding_out_channels": [
|
| 19 |
+
16,
|
| 20 |
+
32,
|
| 21 |
+
96,
|
| 22 |
+
256
|
| 23 |
+
],
|
| 24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"upcast_attention": false,
|
| 51 |
+
"use_linear_projection": false
|
| 52 |
+
}
|
checkpoint/finetune/ade20k/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d52d6c1d57ce18f39fe1f4164236d45ebd93ef894979c75dd67a6b745d2bbb4
|
| 3 |
+
size 1445157120
|
checkpoint/finetune/cocostuff/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"_name_or_path": "lllyasviel/control_v11p_sd15_seg",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"class_embed_type": null,
|
| 17 |
+
"conditioning_channels": 3,
|
| 18 |
+
"conditioning_embedding_out_channels": [
|
| 19 |
+
16,
|
| 20 |
+
32,
|
| 21 |
+
96,
|
| 22 |
+
256
|
| 23 |
+
],
|
| 24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"upcast_attention": false,
|
| 51 |
+
"use_linear_projection": false
|
| 52 |
+
}
|
checkpoint/finetune/cocostuff/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:422ad945d60c86b06614b36d122f9973adaad8e0d2e613dee15d31ff3104e968
|
| 3 |
+
size 1445157120
|
checkpoint/finetune/depth/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"_name_or_path": "lllyasviel/control_v11f1p_sd15_depth",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"class_embed_type": null,
|
| 17 |
+
"conditioning_channels": 3,
|
| 18 |
+
"conditioning_embedding_out_channels": [
|
| 19 |
+
16,
|
| 20 |
+
32,
|
| 21 |
+
96,
|
| 22 |
+
256
|
| 23 |
+
],
|
| 24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"upcast_attention": false,
|
| 51 |
+
"use_linear_projection": false
|
| 52 |
+
}
|
checkpoint/finetune/depth/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e35b70638311dcd15a62f6806bf4d31dde577b2f05419b493ab137247a0f3cf
|
| 3 |
+
size 1445157120
|
checkpoint/finetune/hed/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"_name_or_path": "lllyasviel/control_v11p_sd15_softedge",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"class_embed_type": null,
|
| 17 |
+
"conditioning_channels": 3,
|
| 18 |
+
"conditioning_embedding_out_channels": [
|
| 19 |
+
16,
|
| 20 |
+
32,
|
| 21 |
+
96,
|
| 22 |
+
256
|
| 23 |
+
],
|
| 24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"upcast_attention": false,
|
| 51 |
+
"use_linear_projection": false
|
| 52 |
+
}
|
checkpoint/finetune/hed/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e66821bfc662c93efc21d7caa43b28073013f4f23e0be10b972a96708444fb0
|
| 3 |
+
size 1445157120
|
checkpoint/finetune/lineart/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"_name_or_path": "lllyasviel/control_v11p_sd15_lineart",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"class_embed_type": null,
|
| 17 |
+
"conditioning_channels": 3,
|
| 18 |
+
"conditioning_embedding_out_channels": [
|
| 19 |
+
16,
|
| 20 |
+
32,
|
| 21 |
+
96,
|
| 22 |
+
256
|
| 23 |
+
],
|
| 24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"upcast_attention": false,
|
| 51 |
+
"use_linear_projection": false
|
| 52 |
+
}
|
checkpoint/finetune/lineart/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52c3f6ed12e8ff382307c5501e24a50362da7dc07583135ada887f87c6c30767
|
| 3 |
+
size 1445157120
|
checkpoint/reward/ade20k/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"_name_or_path": "work_dirs/finetune/Captioned_ADE20K/1-5/no-with/Captioned_ADE20K-1.5-no-with_Aug28_03-13-25/checkpoint-15001/ControlNetModel",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"class_embed_type": null,
|
| 17 |
+
"conditioning_channels": 3,
|
| 18 |
+
"conditioning_embedding_out_channels": [
|
| 19 |
+
16,
|
| 20 |
+
32,
|
| 21 |
+
96,
|
| 22 |
+
256
|
| 23 |
+
],
|
| 24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"upcast_attention": false,
|
| 51 |
+
"use_linear_projection": false
|
| 52 |
+
}
|
checkpoint/reward/ade20k/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7475268fe706c9666ebb4f0fa5f85311d392181fcaba7403566bdac1246c7e10
|
| 3 |
+
size 1445157120
|
checkpoint/reward/cocostuff/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"_name_or_path": "work_dirs/finetune/Captioned_COCOStuff/1-5/no-with/Captioned_COCOStuff-1.5-no-with_Aug28_14-51-08/checkpoint-35001/ControlNetModel",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"class_embed_type": null,
|
| 17 |
+
"conditioning_channels": 3,
|
| 18 |
+
"conditioning_embedding_out_channels": [
|
| 19 |
+
16,
|
| 20 |
+
32,
|
| 21 |
+
96,
|
| 22 |
+
256
|
| 23 |
+
],
|
| 24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"upcast_attention": false,
|
| 51 |
+
"use_linear_projection": false
|
| 52 |
+
}
|
checkpoint/reward/cocostuff/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf2bdd7697841bfcca1db22c8bae7caa97db4bc440aaff9ea654ab9a13ed977c
|
| 3 |
+
size 1445157120
|
checkpoint/reward/depth/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"_name_or_path": "work_dirs/finetune/MultiGen20M_depth/1-5/no-with/MultiGen20M_depth-1.5-no-with_Sep10_15-25-35/checkpoint-40001/ControlNetModel",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"class_embed_type": null,
|
| 17 |
+
"conditioning_channels": 3,
|
| 18 |
+
"conditioning_embedding_out_channels": [
|
| 19 |
+
16,
|
| 20 |
+
32,
|
| 21 |
+
96,
|
| 22 |
+
256
|
| 23 |
+
],
|
| 24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"upcast_attention": false,
|
| 51 |
+
"use_linear_projection": false
|
| 52 |
+
}
|
checkpoint/reward/depth/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af2cff2dc04f5475a33ca71c738008d8071ec6041d5269aed82bd1ada9078b1b
|
| 3 |
+
size 1445157120
|
checkpoint/reward/hed/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"_name_or_path": "work_dirs/finetune/MultiGen20M_hed/1-5/no-with/MultiGen20M_hed-1.5-no-with_Sep04_11-22-56/checkpoint-50001/ControlNetModel",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"class_embed_type": null,
|
| 17 |
+
"conditioning_channels": 3,
|
| 18 |
+
"conditioning_embedding_out_channels": [
|
| 19 |
+
16,
|
| 20 |
+
32,
|
| 21 |
+
96,
|
| 22 |
+
256
|
| 23 |
+
],
|
| 24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"upcast_attention": false,
|
| 51 |
+
"use_linear_projection": false
|
| 52 |
+
}
|
checkpoint/reward/hed/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:895e220c5fe15ca8acb9ce76c09a000874a596e35367c74ec4af60a1835166f0
|
| 3 |
+
size 1445157120
|
checkpoint/reward/lineart/config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.30.0",
|
| 4 |
+
"_name_or_path": "work_dirs/finetune/MultiGen20M_linedrawing/1-5/no-with/MultiGen20M_linedrawing-1.5-no-with_Sep04_11-15-03/checkpoint-50001/ControlNetModel",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": 8,
|
| 10 |
+
"block_out_channels": [
|
| 11 |
+
320,
|
| 12 |
+
640,
|
| 13 |
+
1280,
|
| 14 |
+
1280
|
| 15 |
+
],
|
| 16 |
+
"class_embed_type": null,
|
| 17 |
+
"conditioning_channels": 3,
|
| 18 |
+
"conditioning_embedding_out_channels": [
|
| 19 |
+
16,
|
| 20 |
+
32,
|
| 21 |
+
96,
|
| 22 |
+
256
|
| 23 |
+
],
|
| 24 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 25 |
+
"cross_attention_dim": 768,
|
| 26 |
+
"down_block_types": [
|
| 27 |
+
"CrossAttnDownBlock2D",
|
| 28 |
+
"CrossAttnDownBlock2D",
|
| 29 |
+
"CrossAttnDownBlock2D",
|
| 30 |
+
"DownBlock2D"
|
| 31 |
+
],
|
| 32 |
+
"downsample_padding": 1,
|
| 33 |
+
"encoder_hid_dim": null,
|
| 34 |
+
"encoder_hid_dim_type": null,
|
| 35 |
+
"flip_sin_to_cos": true,
|
| 36 |
+
"freq_shift": 0,
|
| 37 |
+
"global_pool_conditions": false,
|
| 38 |
+
"in_channels": 4,
|
| 39 |
+
"layers_per_block": 2,
|
| 40 |
+
"mid_block_scale_factor": 1,
|
| 41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 42 |
+
"norm_eps": 1e-05,
|
| 43 |
+
"norm_num_groups": 32,
|
| 44 |
+
"num_attention_heads": null,
|
| 45 |
+
"num_class_embeds": null,
|
| 46 |
+
"only_cross_attention": false,
|
| 47 |
+
"projection_class_embeddings_input_dim": null,
|
| 48 |
+
"resnet_time_scale_shift": "default",
|
| 49 |
+
"transformer_layers_per_block": 1,
|
| 50 |
+
"upcast_attention": false,
|
| 51 |
+
"use_linear_projection": false
|
| 52 |
+
}
|
checkpoint/reward/lineart/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3076734a09542a402b8534af6eb101a639726fa0d154db45413ba50876e81eef
|
| 3 |
+
size 1445157120
|