CiaraRowles patrickvonplaten commited on
Commit
d47bd9b
1 Parent(s): 50e4b80

Add diffusers weights (#13)

Browse files

- add diffusers weights (777df19242878af168a865881e76b97efd683736)


Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>

README.md CHANGED
@@ -4,6 +4,7 @@ tags:
4
  - controlnet
5
  - stable-diffusion
6
  - diffusers
 
7
  ---
8
  Introducing the Beta Version of TemporalNet
9
 
@@ -35,4 +36,4 @@ Write an Extension for the web ui.
35
 
36
  Write a feature that automatically generates an "init.png" image if none is provided.
37
 
38
- ̶C̶h̶a̶n̶g̶e̶ ̶t̶h̶e̶ ̶e̶x̶t̶e̶n̶s̶i̶o̶n̶ ̶t̶o̶ ̶.̶s̶a̶f̶e̶t̶e̶n̶s̶o̶r̶s̶ ̶a̶n̶d̶ ̶i̶n̶v̶e̶s̶t̶i̶g̶a̶t̶e̶ ̶c̶o̶m̶p̶r̶e̶s̶s̶i̶o̶n̶.̶
 
4
  - controlnet
5
  - stable-diffusion
6
  - diffusers
7
+ base_model: runwayml/stable-diffusion-v1-5
8
  ---
9
  Introducing the Beta Version of TemporalNet
10
 
 
36
 
37
  Write a feature that automatically generates an "init.png" image if none is provided.
38
 
39
+ ̶C̶h̶a̶n̶g̶e̶ ̶t̶h̶e̶ ̶e̶x̶t̶e̶n̶s̶i̶o̶n̶ ̶t̶o̶ ̶.̶s̶a̶f̶e̶t̶e̶n̶s̶o̶r̶s̶ ̶a̶n̶d̶ ̶i̶n̶v̶e̶s̶t̶i̶g̶a̶t̶e̶ ̶c̶o̶m̶p̶r̶e̶s̶s̶i̶o̶n̶.̶
cldm_v15.yaml ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ model:
2
+ target: cldm.cldm.ControlLDM
3
+ params:
4
+ linear_start: 0.00085
5
+ linear_end: 0.0120
6
+ num_timesteps_cond: 1
7
+ log_every_t: 200
8
+ timesteps: 1000
9
+ first_stage_key: "jpg"
10
+ cond_stage_key: "txt"
11
+ control_key: "hint"
12
+ image_size: 64
13
+ channels: 4
14
+ cond_stage_trainable: false
15
+ conditioning_key: crossattn
16
+ monitor: val/loss_simple_ema
17
+ scale_factor: 0.18215
18
+ use_ema: False
19
+ only_mid_control: False
20
+
21
+ control_stage_config:
22
+ target: cldm.cldm.ControlNet
23
+ params:
24
+ image_size: 32 # unused
25
+ in_channels: 4
26
+ hint_channels: 3
27
+ model_channels: 320
28
+ attention_resolutions: [ 4, 2, 1 ]
29
+ num_res_blocks: 2
30
+ channel_mult: [ 1, 2, 4, 4 ]
31
+ num_heads: 8
32
+ use_spatial_transformer: True
33
+ transformer_depth: 1
34
+ context_dim: 768
35
+ use_checkpoint: True
36
+ legacy: False
37
+
38
+ unet_config:
39
+ target: cldm.cldm.ControlledUnetModel
40
+ params:
41
+ image_size: 32 # unused
42
+ in_channels: 4
43
+ out_channels: 4
44
+ model_channels: 320
45
+ attention_resolutions: [ 4, 2, 1 ]
46
+ num_res_blocks: 2
47
+ channel_mult: [ 1, 2, 4, 4 ]
48
+ num_heads: 8
49
+ use_spatial_transformer: True
50
+ transformer_depth: 1
51
+ context_dim: 768
52
+ use_checkpoint: True
53
+ legacy: False
54
+
55
+ first_stage_config:
56
+ target: ldm.models.autoencoder.AutoencoderKL
57
+ params:
58
+ embed_dim: 4
59
+ monitor: val/rec_loss
60
+ ddconfig:
61
+ double_z: true
62
+ z_channels: 4
63
+ resolution: 256
64
+ in_channels: 3
65
+ out_ch: 3
66
+ ch: 128
67
+ ch_mult:
68
+ - 1
69
+ - 2
70
+ - 4
71
+ - 4
72
+ num_res_blocks: 2
73
+ attn_resolutions: []
74
+ dropout: 0.0
75
+ lossconfig:
76
+ target: torch.nn.Identity
77
+
78
+ cond_stage_config:
79
+ target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "_name_or_path": "./",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": 8,
7
+ "block_out_channels": [
8
+ 320,
9
+ 640,
10
+ 1280,
11
+ 1280
12
+ ],
13
+ "class_embed_type": null,
14
+ "conditioning_embedding_out_channels": [
15
+ 16,
16
+ 32,
17
+ 96,
18
+ 256
19
+ ],
20
+ "controlnet_conditioning_channel_order": "rgb",
21
+ "cross_attention_dim": 768,
22
+ "down_block_types": [
23
+ "CrossAttnDownBlock2D",
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "DownBlock2D"
27
+ ],
28
+ "downsample_padding": 1,
29
+ "flip_sin_to_cos": true,
30
+ "freq_shift": 0,
31
+ "in_channels": 4,
32
+ "layers_per_block": 2,
33
+ "mid_block_scale_factor": 1,
34
+ "norm_eps": 1e-05,
35
+ "norm_num_groups": 32,
36
+ "num_class_embeds": null,
37
+ "only_cross_attention": false,
38
+ "projection_class_embeddings_input_dim": null,
39
+ "resnet_time_scale_shift": "default",
40
+ "upcast_attention": false,
41
+ "use_linear_projection": false
42
+ }
diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51b507195e14079d0617e4990fcf6b140fab01080fe076ef96a4a72d49ff316e
3
+ size 1445254969
diffusion_pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61572d3d587beabc5dcd439d1559b64b67ac8f449e9c6d04de734475ca850df7
3
+ size 722698343
diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:671aa7e3697a2c089287962e896b620285cee8be62ef73e34d35d4a23a6fd019
3
+ size 722598642
diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0dca33b7a1ac6de2920de1f335816d5af60bdc68f9c57d8b9282b46811e3c2
3
+ size 1445157124