akhaliq HF staff commited on
Commit
7c0f8b0
1 Parent(s): ce66cd8

Add Diffusers weights

Browse files

Add Diffusers weights converted from checkpoint `v2-1-0.ckpt` in revision ce66cd87f1360f738348b669b3ecbb79e3c6b8bf

model_index.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.11.1",
4
  "feature_extractor": [
5
  null,
6
  null
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.11.0.dev0",
4
  "feature_extractor": [
5
  null,
6
  null
scheduler/scheduler_config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "_class_name": "PNDMScheduler",
3
- "_diffusers_version": "0.11.1",
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
  "set_alpha_to_one": false,
11
  "skip_prk_steps": true,
12
  "steps_offset": 1,
 
1
  {
2
  "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.11.0.dev0",
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": "v_prediction",
10
  "set_alpha_to_one": false,
11
  "skip_prk_steps": true,
12
  "steps_offset": 1,
text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "stabilityai/stable-diffusion-2-1-base",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -20,6 +20,6 @@
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
  "torch_dtype": "float32",
23
- "transformers_version": "4.25.1",
24
  "vocab_size": 49408
25
  }
 
1
  {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
  "torch_dtype": "float32",
23
+ "transformers_version": "4.26.0.dev0",
24
  "vocab_size": 49408
25
  }
text_encoder/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3e254d7b61353497ea0be2c4013df4ea8f739ee88cffa0ba58cd085459ed565
3
- size 1361671895
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2188379b05015f531d61503e714234d00a64939792f3098b324e516547f0194f
3
+ size 1361674657
tokenizer/tokenizer_config.json CHANGED
@@ -19,7 +19,7 @@
19
  },
20
  "errors": "replace",
21
  "model_max_length": 77,
22
- "name_or_path": "stabilityai/stable-diffusion-2-1-base",
23
  "pad_token": "<|endoftext|>",
24
  "special_tokens_map_file": "./special_tokens_map.json",
25
  "tokenizer_class": "CLIPTokenizer",
 
19
  },
20
  "errors": "replace",
21
  "model_max_length": 77,
22
+ "name_or_path": "stabilityai/stable-diffusion-2",
23
  "pad_token": "<|endoftext|>",
24
  "special_tokens_map_file": "./special_tokens_map.json",
25
  "tokenizer_class": "CLIPTokenizer",
unet/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.11.1",
4
  "act_fn": "silu",
5
  "attention_head_dim": [
6
  5,
@@ -15,7 +15,6 @@
15
  1280
16
  ],
17
  "center_input_sample": false,
18
- "class_embed_type": null,
19
  "cross_attention_dim": 1024,
20
  "down_block_types": [
21
  "CrossAttnDownBlock2D",
@@ -30,20 +29,18 @@
30
  "in_channels": 4,
31
  "layers_per_block": 2,
32
  "mid_block_scale_factor": 1,
33
- "mid_block_type": "UNetMidBlock2DCrossAttn",
34
  "norm_eps": 1e-05,
35
  "norm_num_groups": 32,
36
  "num_class_embeds": null,
37
  "only_cross_attention": false,
38
  "out_channels": 4,
39
- "resnet_time_scale_shift": "default",
40
- "sample_size": 64,
41
  "up_block_types": [
42
  "UpBlock2D",
43
  "CrossAttnUpBlock2D",
44
  "CrossAttnUpBlock2D",
45
  "CrossAttnUpBlock2D"
46
  ],
47
- "upcast_attention": false,
48
  "use_linear_projection": true
49
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.11.0.dev0",
4
  "act_fn": "silu",
5
  "attention_head_dim": [
6
  5,
 
15
  1280
16
  ],
17
  "center_input_sample": false,
 
18
  "cross_attention_dim": 1024,
19
  "down_block_types": [
20
  "CrossAttnDownBlock2D",
 
29
  "in_channels": 4,
30
  "layers_per_block": 2,
31
  "mid_block_scale_factor": 1,
 
32
  "norm_eps": 1e-05,
33
  "norm_num_groups": 32,
34
  "num_class_embeds": null,
35
  "only_cross_attention": false,
36
  "out_channels": 4,
37
+ "sample_size": 96,
 
38
  "up_block_types": [
39
  "UpBlock2D",
40
  "CrossAttnUpBlock2D",
41
  "CrossAttnUpBlock2D",
42
  "CrossAttnUpBlock2D"
43
  ],
44
+ "upcast_attention": true,
45
  "use_linear_projection": true
46
  }
unet/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de981f842c293d09c674830a093379212a6213ccf0e860b811f4885114a8b929
3
- size 3463913445
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dce504d78cc7f2dc8ee8141cd52cd29ea4589dffe7f6ab72f71717987578e056
3
+ size 3463925093
vae/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.11.1",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
@@ -19,7 +19,7 @@
19
  "layers_per_block": 2,
20
  "norm_num_groups": 32,
21
  "out_channels": 3,
22
- "sample_size": 512,
23
  "up_block_types": [
24
  "UpDecoderBlock2D",
25
  "UpDecoderBlock2D",
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.11.0.dev0",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
 
19
  "layers_per_block": 2,
20
  "norm_num_groups": 32,
21
  "out_channels": 3,
22
+ "sample_size": 768,
23
  "up_block_types": [
24
  "UpDecoderBlock2D",
25
  "UpDecoderBlock2D",
vae/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f9c393b8c32f1f8a280b1ec8b18f835f9325658e68cbf3268c873a19dbc40f4
3
- size 334707217
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b937b3147b1e4a64d559cee0ee27d5b978c06c18d99bcf5c7417675d627f88b4
3
+ size 334711857