idlebg commited on
Commit
35fb944
1 Parent(s): 5fc3ee3

Adding `diffusers` weights of this model

Browse files

This PR adds fp32 and fp16 weights in PyTorch and safetensors format to FFusion/FFusion-BaSE

model_index.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.10.2",
4
  "feature_extractor": [
5
  null,
6
  null
7
  ],
8
- "requires_safety_checker": null,
9
  "safety_checker": [
10
  null,
11
  null
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.19.0.dev0",
4
  "feature_extractor": [
5
  null,
6
  null
7
  ],
8
+ "requires_safety_checker": false,
9
  "safety_checker": [
10
  null,
11
  null
scheduler/scheduler_config.json CHANGED
@@ -1,14 +1,19 @@
1
  {
2
  "_class_name": "DDIMScheduler",
3
- "_diffusers_version": "0.10.2",
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": "v_prediction",
 
 
10
  "set_alpha_to_one": false,
11
- "skip_prk_steps": true,
12
  "steps_offset": 1,
 
 
13
  "trained_betas": null
14
  }
 
1
  {
2
  "_class_name": "DDIMScheduler",
3
+ "_diffusers_version": "0.19.0.dev0",
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": "v_prediction",
12
+ "rescale_betas_zero_snr": false,
13
+ "sample_max_value": 1.0,
14
  "set_alpha_to_one": false,
 
15
  "steps_offset": 1,
16
+ "thresholding": false,
17
+ "timestep_spacing": "leading",
18
  "trained_betas": null
19
  }
text_encoder/config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "CLIPTextModel"
4
  ],
@@ -18,7 +19,7 @@
18
  "num_hidden_layers": 23,
19
  "pad_token_id": 1,
20
  "projection_dim": 512,
21
- "torch_dtype": "float32",
22
- "transformers_version": "4.26.0",
23
  "vocab_size": 49408
24
  }
 
1
  {
2
+ "_name_or_path": "hf-models/stable-diffusion-v2-768x768/text_encoder",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
19
  "num_hidden_layers": 23,
20
  "pad_token_id": 1,
21
  "projection_dim": 512,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
  "vocab_size": 49408
25
  }
text_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27abfac2a818730effdf31368547e447a228230e5c0fa0d6cd67dffe7edf4f3
3
+ size 680820392
text_encoder/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e400fca9292630a9647d4a046b8f23b8d625cafdc077102313c83d3e6c21c64
3
- size 1361597016
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9c407c896a28b174b59eb4b65634b909fbb8f8183cc90927b88866ad9831771
3
+ size 1168458360
text_encoder/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aeb0c8eec01e768ad0a8b2c2c3804297a05b750768628167469f38411bba29da
3
- size 1361674657
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c78800b3082d1bbbf1d0f6ecdf0f2a278da7207c34370c55142374b9a22a13
3
+ size 1361655149
text_encoder/pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4db18e4fced8981288f10a05cea6fd51691f1080a2b71534ada82cc93134e90e
3
+ size 680899947
tokenizer/tokenizer_config.json CHANGED
@@ -8,6 +8,7 @@
8
  "rstrip": false,
9
  "single_word": false
10
  },
 
11
  "do_lower_case": true,
12
  "eos_token": {
13
  "__type": "AddedToken",
@@ -19,9 +20,7 @@
19
  },
20
  "errors": "replace",
21
  "model_max_length": 77,
22
- "name_or_path": "stabilityai/stable-diffusion-2-1",
23
  "pad_token": "<|endoftext|>",
24
- "special_tokens_map_file": "./special_tokens_map.json",
25
  "tokenizer_class": "CLIPTokenizer",
26
  "unk_token": {
27
  "__type": "AddedToken",
 
8
  "rstrip": false,
9
  "single_word": false
10
  },
11
+ "clean_up_tokenization_spaces": true,
12
  "do_lower_case": true,
13
  "eos_token": {
14
  "__type": "AddedToken",
 
20
  },
21
  "errors": "replace",
22
  "model_max_length": 77,
 
23
  "pad_token": "<|endoftext|>",
 
24
  "tokenizer_class": "CLIPTokenizer",
25
  "unk_token": {
26
  "__type": "AddedToken",
unet/config.json CHANGED
@@ -1,7 +1,10 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.10.2",
4
  "act_fn": "silu",
 
 
 
5
  "attention_head_dim": [
6
  5,
7
  10,
@@ -15,7 +18,12 @@
15
  1280
16
  ],
17
  "center_input_sample": false,
 
 
 
 
18
  "cross_attention_dim": 1024,
 
19
  "down_block_types": [
20
  "CrossAttnDownBlock2D",
21
  "CrossAttnDownBlock2D",
@@ -24,23 +32,38 @@
24
  ],
25
  "downsample_padding": 1,
26
  "dual_cross_attention": false,
 
 
27
  "flip_sin_to_cos": true,
28
  "freq_shift": 0,
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": 64,
 
 
 
 
 
 
 
 
 
 
38
  "up_block_types": [
39
  "UpBlock2D",
40
  "CrossAttnUpBlock2D",
41
  "CrossAttnUpBlock2D",
42
  "CrossAttnUpBlock2D"
43
  ],
44
- "upcast_attention": false,
45
  "use_linear_projection": true
46
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.19.0.dev0",
4
  "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
  "attention_head_dim": [
9
  5,
10
  10,
 
18
  1280
19
  ],
20
  "center_input_sample": false,
21
+ "class_embed_type": null,
22
+ "class_embeddings_concat": false,
23
+ "conv_in_kernel": 3,
24
+ "conv_out_kernel": 3,
25
  "cross_attention_dim": 1024,
26
+ "cross_attention_norm": null,
27
  "down_block_types": [
28
  "CrossAttnDownBlock2D",
29
  "CrossAttnDownBlock2D",
 
32
  ],
33
  "downsample_padding": 1,
34
  "dual_cross_attention": false,
35
+ "encoder_hid_dim": null,
36
+ "encoder_hid_dim_type": null,
37
  "flip_sin_to_cos": true,
38
  "freq_shift": 0,
39
  "in_channels": 4,
40
  "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
  "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
  "norm_eps": 1e-05,
45
  "norm_num_groups": 32,
46
+ "num_attention_heads": null,
47
  "num_class_embeds": null,
48
  "only_cross_attention": false,
49
  "out_channels": 4,
50
+ "projection_class_embeddings_input_dim": null,
51
+ "resnet_out_scale_factor": 1.0,
52
+ "resnet_skip_time_act": false,
53
+ "resnet_time_scale_shift": "default",
54
+ "sample_size": 96,
55
+ "time_cond_proj_dim": null,
56
+ "time_embedding_act_fn": null,
57
+ "time_embedding_dim": null,
58
+ "time_embedding_type": "positional",
59
+ "timestep_post_act": null,
60
+ "transformer_layers_per_block": 1,
61
  "up_block_types": [
62
  "UpBlock2D",
63
  "CrossAttnUpBlock2D",
64
  "CrossAttnUpBlock2D",
65
  "CrossAttnUpBlock2D"
66
  ],
67
+ "upcast_attention": null,
68
  "use_linear_projection": true
69
  }
unet/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09b7edb76bebc5dbcf128424c54bae9793bcff43cee0e17cc35f0663e11e0adf
3
  size 3463925093
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:509bb04d8940dba0f28c0200084936d26fa1885961367f45305a5eb386d9ac79
3
  size 3463925093
unet/diffusion_pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e48d95bec4a63c348a09bb319ae7e9f64120e677c9023b04f9667516640c92
3
+ size 1732107093
unet/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f58da91d7052213c5831efadffb1bbc8e1e9eebeccb0b8d3961f619f95dcdd31
3
+ size 1731904736
vae/config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.10.2",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
@@ -14,12 +14,14 @@
14
  "DownEncoderBlock2D",
15
  "DownEncoderBlock2D"
16
  ],
 
17
  "in_channels": 3,
18
  "latent_channels": 4,
19
  "layers_per_block": 2,
20
  "norm_num_groups": 32,
21
  "out_channels": 3,
22
- "sample_size": 256,
 
23
  "up_block_types": [
24
  "UpDecoderBlock2D",
25
  "UpDecoderBlock2D",
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.19.0.dev0",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
 
14
  "DownEncoderBlock2D",
15
  "DownEncoderBlock2D"
16
  ],
17
+ "force_upcast": true,
18
  "in_channels": 3,
19
  "latent_channels": 4,
20
  "layers_per_block": 2,
21
  "norm_num_groups": 32,
22
  "out_channels": 3,
23
+ "sample_size": 768,
24
+ "scaling_factor": 0.18215,
25
  "up_block_types": [
26
  "UpDecoderBlock2D",
27
  "UpDecoderBlock2D",
vae/diffusion_pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edd1d1807563c2d1c8c5ab84dfc2f455fcad0064727d264dd5172c569b5c45b2
3
- size 334711857
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eaa055d84ddad2df8593f4a3a2fdc58a905ecf2f17dee42e9bca32f70373b59
3
+ size 334712113
vae/diffusion_pytorch_model.fp16.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d55c592ee39c6619b6c0232057b7979bbb8b8c91bcde23e4216c7d7a54b2768
3
+ size 167405651
vae/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b6885891b67baa7f872fe9d00c44acd1cfd72475d289d83d93031ea8b32115
3
+ size 167335342
vae/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f14834bedf1e853c99644d00c92404f185e2798de52337f8fb6bb5bddb48703
3
- size 334643276
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b6e3f78759255c499bd0b1c3a4c3c9ecf4e489d09f7b21225906dabfb3ce3c
3
+ size 334643268