Hugging Face's logo

Spaces:
Wuvin
/
Unique3D
Running on Zero

App Files Community
18
hysts HF staff commited on
Commit
62283ad
·
1 Parent(s): fc219b8

Remove ckpt/

Browse files
Files changed (24) hide show
  1. ckpt/controlnet-tile/config.json +0 -52
  2. ckpt/controlnet-tile/diffusion_pytorch_model.safetensors +0 -3
  3. ckpt/image2normal/feature_extractor/preprocessor_config.json +0 -44
  4. ckpt/image2normal/image_encoder/config.json +0 -23
  5. ckpt/image2normal/image_encoder/model.safetensors +0 -3
  6. ckpt/image2normal/model_index.json +0 -31
  7. ckpt/image2normal/scheduler/scheduler_config.json +0 -16
  8. ckpt/image2normal/unet/config.json +0 -68
  9. ckpt/image2normal/unet/diffusion_pytorch_model.safetensors +0 -3
  10. ckpt/image2normal/unet_state_dict.pth +0 -3
  11. ckpt/image2normal/vae/config.json +0 -34
  12. ckpt/image2normal/vae/diffusion_pytorch_model.safetensors +0 -3
  13. ckpt/img2mvimg/feature_extractor/preprocessor_config.json +0 -44
  14. ckpt/img2mvimg/image_encoder/config.json +0 -23
  15. ckpt/img2mvimg/image_encoder/model.safetensors +0 -3
  16. ckpt/img2mvimg/model_index.json +0 -31
  17. ckpt/img2mvimg/scheduler/scheduler_config.json +0 -20
  18. ckpt/img2mvimg/unet/config.json +0 -68
  19. ckpt/img2mvimg/unet/diffusion_pytorch_model.safetensors +0 -3
  20. ckpt/img2mvimg/unet_state_dict.pth +0 -3
  21. ckpt/img2mvimg/vae/config.json +0 -34
  22. ckpt/img2mvimg/vae/diffusion_pytorch_model.safetensors +0 -3
  23. ckpt/realesrgan-x4.onnx +0 -3
  24. ckpt/v1-inference.yaml +0 -70
ckpt/controlnet-tile/config.json DELETED
@@ -1,52 +0,0 @@
1
- {
2
- "_class_name": "ControlNetModel",
3
- "_diffusers_version": "0.27.2",
4
- "_name_or_path": "lllyasviel/control_v11f1e_sd15_tile",
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/controlnet-tile/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:845d3845053912728cd1453029a0ef87d3c0a3082a083ba393f36eaa5fb0e218
3
- size 1445157120
 
 
 
 
ckpt/image2normal/feature_extractor/preprocessor_config.json DELETED
@@ -1,44 +0,0 @@
1
- {
2
- "_valid_processor_keys": [
3
- "images",
4
- "do_resize",
5
- "size",
6
- "resample",
7
- "do_center_crop",
8
- "crop_size",
9
- "do_rescale",
10
- "rescale_factor",
11
- "do_normalize",
12
- "image_mean",
13
- "image_std",
14
- "do_convert_rgb",
15
- "return_tensors",
16
- "data_format",
17
- "input_data_format"
18
- ],
19
- "crop_size": {
20
- "height": 224,
21
- "width": 224
22
- },
23
- "do_center_crop": true,
24
- "do_convert_rgb": true,
25
- "do_normalize": true,
26
- "do_rescale": true,
27
- "do_resize": true,
28
- "image_mean": [
29
- 0.48145466,
30
- 0.4578275,
31
- 0.40821073
32
- ],
33
- "image_processor_type": "CLIPImageProcessor",
34
- "image_std": [
35
- 0.26862954,
36
- 0.26130258,
37
- 0.27577711
38
- ],
39
- "resample": 3,
40
- "rescale_factor": 0.00392156862745098,
41
- "size": {
42
- "shortest_edge": 224
43
- }
44
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/image2normal/image_encoder/config.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
3
- "architectures": [
4
- "CLIPVisionModelWithProjection"
5
- ],
6
- "attention_dropout": 0.0,
7
- "dropout": 0.0,
8
- "hidden_act": "quick_gelu",
9
- "hidden_size": 1024,
10
- "image_size": 224,
11
- "initializer_factor": 1.0,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 4096,
14
- "layer_norm_eps": 1e-05,
15
- "model_type": "clip_vision_model",
16
- "num_attention_heads": 16,
17
- "num_channels": 3,
18
- "num_hidden_layers": 24,
19
- "patch_size": 14,
20
- "projection_dim": 768,
21
- "torch_dtype": "bfloat16",
22
- "transformers_version": "4.39.3"
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/image2normal/image_encoder/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4b33d864f89a793357a768cb07d0dc18d6a14e6664f4110a0d535ca9ba78da8
3
- size 607980488
 
 
 
 
ckpt/image2normal/model_index.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "_class_name": "StableDiffusionImageCustomPipeline",
3
- "_diffusers_version": "0.27.2",
4
- "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
5
- "feature_extractor": [
6
- "transformers",
7
- "CLIPImageProcessor"
8
- ],
9
- "image_encoder": [
10
- "transformers",
11
- "CLIPVisionModelWithProjection"
12
- ],
13
- "noisy_cond_latents": false,
14
- "requires_safety_checker": true,
15
- "safety_checker": [
16
- null,
17
- null
18
- ],
19
- "scheduler": [
20
- "diffusers",
21
- "EulerAncestralDiscreteScheduler"
22
- ],
23
- "unet": [
24
- "diffusers",
25
- "UNet2DConditionModel"
26
- ],
27
- "vae": [
28
- "diffusers",
29
- "AutoencoderKL"
30
- ]
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/image2normal/scheduler/scheduler_config.json DELETED
@@ -1,16 +0,0 @@
1
- {
2
- "_class_name": "EulerAncestralDiscreteScheduler",
3
- "_diffusers_version": "0.27.2",
4
- "beta_end": 0.012,
5
- "beta_schedule": "scaled_linear",
6
- "beta_start": 0.00085,
7
- "clip_sample": false,
8
- "num_train_timesteps": 1000,
9
- "prediction_type": "epsilon",
10
- "rescale_betas_zero_snr": false,
11
- "set_alpha_to_one": false,
12
- "skip_prk_steps": true,
13
- "steps_offset": 1,
14
- "timestep_spacing": "linspace",
15
- "trained_betas": null
16
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/image2normal/unet/config.json DELETED
@@ -1,68 +0,0 @@
1
- {
2
- "_class_name": "UnifieldWrappedUNet",
3
- "_diffusers_version": "0.27.2",
4
- "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
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
- "attention_type": "default",
11
- "block_out_channels": [
12
- 320,
13
- 640,
14
- 1280,
15
- 1280
16
- ],
17
- "center_input_sample": false,
18
- "class_embed_type": null,
19
- "class_embeddings_concat": false,
20
- "conv_in_kernel": 3,
21
- "conv_out_kernel": 3,
22
- "cross_attention_dim": 768,
23
- "cross_attention_norm": null,
24
- "down_block_types": [
25
- "CrossAttnDownBlock2D",
26
- "CrossAttnDownBlock2D",
27
- "CrossAttnDownBlock2D",
28
- "DownBlock2D"
29
- ],
30
- "downsample_padding": 1,
31
- "dropout": 0.0,
32
- "dual_cross_attention": false,
33
- "encoder_hid_dim": null,
34
- "encoder_hid_dim_type": null,
35
- "flip_sin_to_cos": true,
36
- "freq_shift": 0,
37
- "in_channels": 4,
38
- "layers_per_block": 2,
39
- "mid_block_only_cross_attention": null,
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
- "out_channels": 4,
48
- "projection_class_embeddings_input_dim": null,
49
- "resnet_out_scale_factor": 1.0,
50
- "resnet_skip_time_act": false,
51
- "resnet_time_scale_shift": "default",
52
- "reverse_transformer_layers_per_block": null,
53
- "sample_size": 64,
54
- "time_cond_proj_dim": null,
55
- "time_embedding_act_fn": null,
56
- "time_embedding_dim": null,
57
- "time_embedding_type": "positional",
58
- "timestep_post_act": null,
59
- "transformer_layers_per_block": 1,
60
- "up_block_types": [
61
- "UpBlock2D",
62
- "CrossAttnUpBlock2D",
63
- "CrossAttnUpBlock2D",
64
- "CrossAttnUpBlock2D"
65
- ],
66
- "upcast_attention": false,
67
- "use_linear_projection": false
68
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/image2normal/unet/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5cbaf1d56619345ce78de8cfbb20d94923b3305a364bf6a5b2a2cc422d4b701
3
- size 3537503456
 
 
 
 
ckpt/image2normal/unet_state_dict.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8df80d09e953d338aa6d8decd0351c5045f52ec6e2645eee2027ccb8792c8ed8
3
- size 3537964654
 
 
 
 
ckpt/image2normal/vae/config.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.27.2",
4
- "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
5
- "act_fn": "silu",
6
- "block_out_channels": [
7
- 128,
8
- 256,
9
- 512,
10
- 512
11
- ],
12
- "down_block_types": [
13
- "DownEncoderBlock2D",
14
- "DownEncoderBlock2D",
15
- "DownEncoderBlock2D",
16
- "DownEncoderBlock2D"
17
- ],
18
- "force_upcast": true,
19
- "in_channels": 3,
20
- "latent_channels": 4,
21
- "latents_mean": null,
22
- "latents_std": null,
23
- "layers_per_block": 2,
24
- "norm_num_groups": 32,
25
- "out_channels": 3,
26
- "sample_size": 256,
27
- "scaling_factor": 0.18215,
28
- "up_block_types": [
29
- "UpDecoderBlock2D",
30
- "UpDecoderBlock2D",
31
- "UpDecoderBlock2D",
32
- "UpDecoderBlock2D"
33
- ]
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/image2normal/vae/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d0c34f57abe50f323040f2366c8e22b941068dcdf53c8eb1d6fafb838afecb7
3
- size 167335590
 
 
 
 
ckpt/img2mvimg/feature_extractor/preprocessor_config.json DELETED
@@ -1,44 +0,0 @@
1
- {
2
- "_valid_processor_keys": [
3
- "images",
4
- "do_resize",
5
- "size",
6
- "resample",
7
- "do_center_crop",
8
- "crop_size",
9
- "do_rescale",
10
- "rescale_factor",
11
- "do_normalize",
12
- "image_mean",
13
- "image_std",
14
- "do_convert_rgb",
15
- "return_tensors",
16
- "data_format",
17
- "input_data_format"
18
- ],
19
- "crop_size": {
20
- "height": 224,
21
- "width": 224
22
- },
23
- "do_center_crop": true,
24
- "do_convert_rgb": true,
25
- "do_normalize": true,
26
- "do_rescale": true,
27
- "do_resize": true,
28
- "image_mean": [
29
- 0.48145466,
30
- 0.4578275,
31
- 0.40821073
32
- ],
33
- "image_processor_type": "CLIPImageProcessor",
34
- "image_std": [
35
- 0.26862954,
36
- 0.26130258,
37
- 0.27577711
38
- ],
39
- "resample": 3,
40
- "rescale_factor": 0.00392156862745098,
41
- "size": {
42
- "shortest_edge": 224
43
- }
44
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/img2mvimg/image_encoder/config.json DELETED
@@ -1,23 +0,0 @@
1
- {
2
- "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
3
- "architectures": [
4
- "CLIPVisionModelWithProjection"
5
- ],
6
- "attention_dropout": 0.0,
7
- "dropout": 0.0,
8
- "hidden_act": "quick_gelu",
9
- "hidden_size": 1024,
10
- "image_size": 224,
11
- "initializer_factor": 1.0,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 4096,
14
- "layer_norm_eps": 1e-05,
15
- "model_type": "clip_vision_model",
16
- "num_attention_heads": 16,
17
- "num_channels": 3,
18
- "num_hidden_layers": 24,
19
- "patch_size": 14,
20
- "projection_dim": 768,
21
- "torch_dtype": "float32",
22
- "transformers_version": "4.39.3"
23
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/img2mvimg/image_encoder/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:77b33d2a3a643650857672e880ccf73adbaf114fbbadec36d142ee9d48af7e20
3
- size 1215912728
 
 
 
 
ckpt/img2mvimg/model_index.json DELETED
@@ -1,31 +0,0 @@
1
- {
2
- "_class_name": "StableDiffusionImage2MVCustomPipeline",
3
- "_diffusers_version": "0.27.2",
4
- "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
5
- "condition_offset": true,
6
- "feature_extractor": [
7
- "transformers",
8
- "CLIPImageProcessor"
9
- ],
10
- "image_encoder": [
11
- "transformers",
12
- "CLIPVisionModelWithProjection"
13
- ],
14
- "requires_safety_checker": true,
15
- "safety_checker": [
16
- null,
17
- null
18
- ],
19
- "scheduler": [
20
- "diffusers",
21
- "DDIMScheduler"
22
- ],
23
- "unet": [
24
- "diffusers",
25
- "UNet2DConditionModel"
26
- ],
27
- "vae": [
28
- "diffusers",
29
- "AutoencoderKL"
30
- ]
31
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/img2mvimg/scheduler/scheduler_config.json DELETED
@@ -1,20 +0,0 @@
1
- {
2
- "_class_name": "DDIMScheduler",
3
- "_diffusers_version": "0.27.2",
4
- "beta_end": 0.012,
5
- "beta_schedule": "scaled_linear",
6
- "beta_start": 0.00085,
7
- "clip_sample": false,
8
- "clip_sample_range": 1.0,
9
- "dynamic_thresholding_ratio": 0.995,
10
- "num_train_timesteps": 1000,
11
- "prediction_type": "epsilon",
12
- "rescale_betas_zero_snr": false,
13
- "sample_max_value": 1.0,
14
- "set_alpha_to_one": false,
15
- "skip_prk_steps": true,
16
- "steps_offset": 1,
17
- "thresholding": false,
18
- "timestep_spacing": "leading",
19
- "trained_betas": null
20
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/img2mvimg/unet/config.json DELETED
@@ -1,68 +0,0 @@
1
- {
2
- "_class_name": "UnifieldWrappedUNet",
3
- "_diffusers_version": "0.27.2",
4
- "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
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
- "attention_type": "default",
11
- "block_out_channels": [
12
- 320,
13
- 640,
14
- 1280,
15
- 1280
16
- ],
17
- "center_input_sample": false,
18
- "class_embed_type": null,
19
- "class_embeddings_concat": false,
20
- "conv_in_kernel": 3,
21
- "conv_out_kernel": 3,
22
- "cross_attention_dim": 768,
23
- "cross_attention_norm": null,
24
- "down_block_types": [
25
- "CrossAttnDownBlock2D",
26
- "CrossAttnDownBlock2D",
27
- "CrossAttnDownBlock2D",
28
- "DownBlock2D"
29
- ],
30
- "downsample_padding": 1,
31
- "dropout": 0.0,
32
- "dual_cross_attention": false,
33
- "encoder_hid_dim": null,
34
- "encoder_hid_dim_type": null,
35
- "flip_sin_to_cos": true,
36
- "freq_shift": 0,
37
- "in_channels": 8,
38
- "layers_per_block": 2,
39
- "mid_block_only_cross_attention": null,
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": 8,
46
- "only_cross_attention": false,
47
- "out_channels": 4,
48
- "projection_class_embeddings_input_dim": null,
49
- "resnet_out_scale_factor": 1.0,
50
- "resnet_skip_time_act": false,
51
- "resnet_time_scale_shift": "default",
52
- "reverse_transformer_layers_per_block": null,
53
- "sample_size": 64,
54
- "time_cond_proj_dim": null,
55
- "time_embedding_act_fn": null,
56
- "time_embedding_dim": null,
57
- "time_embedding_type": "positional",
58
- "timestep_post_act": null,
59
- "transformer_layers_per_block": 1,
60
- "up_block_types": [
61
- "UpBlock2D",
62
- "CrossAttnUpBlock2D",
63
- "CrossAttnUpBlock2D",
64
- "CrossAttnUpBlock2D"
65
- ],
66
- "upcast_attention": false,
67
- "use_linear_projection": false
68
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/img2mvimg/unet/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:93a3b4e678efac0c997e76df465df13136a4b0f1732e534a1200fad9e04cd0f9
3
- size 3438254688
 
 
 
 
ckpt/img2mvimg/unet_state_dict.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0dff2fdba450af0e10c3a847ba66a530170be2e9b9c9f4c834483515e82738b5
3
- size 3438460972
 
 
 
 
ckpt/img2mvimg/vae/config.json DELETED
@@ -1,34 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.27.2",
4
- "_name_or_path": "lambdalabs/sd-image-variations-diffusers",
5
- "act_fn": "silu",
6
- "block_out_channels": [
7
- 128,
8
- 256,
9
- 512,
10
- 512
11
- ],
12
- "down_block_types": [
13
- "DownEncoderBlock2D",
14
- "DownEncoderBlock2D",
15
- "DownEncoderBlock2D",
16
- "DownEncoderBlock2D"
17
- ],
18
- "force_upcast": true,
19
- "in_channels": 3,
20
- "latent_channels": 4,
21
- "latents_mean": null,
22
- "latents_std": null,
23
- "layers_per_block": 2,
24
- "norm_num_groups": 32,
25
- "out_channels": 3,
26
- "sample_size": 256,
27
- "scaling_factor": 0.18215,
28
- "up_block_types": [
29
- "UpDecoderBlock2D",
30
- "UpDecoderBlock2D",
31
- "UpDecoderBlock2D",
32
- "UpDecoderBlock2D"
33
- ]
34
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ckpt/img2mvimg/vae/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2aa1f43011b553a4cba7f37456465cdbd48aab7b54b9348b890e8058ea7683ec
3
- size 334643268
 
 
 
 
ckpt/realesrgan-x4.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bc5d0c85207adad8bca26286f0c0007f266f85e7aa7c454c565da9b5f3c940a
3
- size 67051617
 
 
 
 
ckpt/v1-inference.yaml DELETED
@@ -1,70 +0,0 @@
1
- model:
2
- base_learning_rate: 1.0e-04
3
- target: ldm.models.diffusion.ddpm.LatentDiffusion
4
- params:
5
- linear_start: 0.00085
6
- linear_end: 0.0120
7
- num_timesteps_cond: 1
8
- log_every_t: 200
9
- timesteps: 1000
10
- first_stage_key: "jpg"
11
- cond_stage_key: "txt"
12
- image_size: 64
13
- channels: 4
14
- cond_stage_trainable: false # Note: different from the one we trained before
15
- conditioning_key: crossattn
16
- monitor: val/loss_simple_ema
17
- scale_factor: 0.18215
18
- use_ema: False
19
-
20
- scheduler_config: # 10000 warmup steps
21
- target: ldm.lr_scheduler.LambdaLinearScheduler
22
- params:
23
- warm_up_steps: [ 10000 ]
24
- cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
25
- f_start: [ 1.e-6 ]
26
- f_max: [ 1. ]
27
- f_min: [ 1. ]
28
-
29
- unet_config:
30
- target: ldm.modules.diffusionmodules.openaimodel.UNetModel
31
- params:
32
- image_size: 32 # unused
33
- in_channels: 4
34
- out_channels: 4
35
- model_channels: 320
36
- attention_resolutions: [ 4, 2, 1 ]
37
- num_res_blocks: 2
38
- channel_mult: [ 1, 2, 4, 4 ]
39
- num_heads: 8
40
- use_spatial_transformer: True
41
- transformer_depth: 1
42
- context_dim: 768
43
- use_checkpoint: True
44
- legacy: False
45
-
46
- first_stage_config:
47
- target: ldm.models.autoencoder.AutoencoderKL
48
- params:
49
- embed_dim: 4
50
- monitor: val/rec_loss
51
- ddconfig:
52
- double_z: true
53
- z_channels: 4
54
- resolution: 256
55
- in_channels: 3
56
- out_ch: 3
57
- ch: 128
58
- ch_mult:
59
- - 1
60
- - 2
61
- - 4
62
- - 4
63
- num_res_blocks: 2
64
- attn_resolutions: []
65
- dropout: 0.0
66
- lossconfig:
67
- target: torch.nn.Identity
68
-
69
- cond_stage_config:
70
- target: ldm.modules.encoders.modules.FrozenCLIPEmbedder