Hugging Face's logo

baidu
/
ERNIE-Image-Turbo

Text-to-Image
Diffusers
Safetensors
ErnieImagePipeline
8B
Model card Files
xet
 Community
3
HsiaX commited on
Commit
c47b737
·
verified ·
1 Parent(s): 05eeef4

Delete files * with huggingface_hub

Browse files
Files changed (17) hide show
  1. pe/chat_template.jinja +0 -21
  2. pe/config.json +0 -38
  3. pe/generation_config.json +0 -8
  4. pe/model.safetensors +0 -3
  5. pe/tokenizer.json +0 -3
  6. pe/tokenizer_config.json +0 -15
  7. scheduler/scheduler_config.json +0 -18
  8. text_encoder/config.json +0 -67
  9. text_encoder/model.safetensors +0 -3
  10. tokenizer/tokenizer.json +0 -3
  11. tokenizer/tokenizer_config.json +0 -15
  12. transformer/config.json +0 -20
  13. transformer/diffusion_pytorch_model-00001-of-00002.safetensors +0 -3
  14. transformer/diffusion_pytorch_model-00002-of-00002.safetensors +0 -3
  15. transformer/diffusion_pytorch_model.safetensors.index.json +0 -416
  16. vae/config.json +0 -40
  17. vae/diffusion_pytorch_model.safetensors +0 -3
pe/chat_template.jinja DELETED
@@ -1,21 +0,0 @@
1
- {#- Chat template for Ministral-3B prompt-enhance fine-tuning.
2
-
3
- Format: <s>{system}\ninput: {user}\n\noutput: {assistant}</s>
4
-
5
- Uses {% generation %} markers so that the loss is computed only on
6
- the assistant response (the output part).
7
- -#}
8
- {%- set sp = "你是一个专业的文生图 Prompt 增强助手。你将收到用户的简短图片描述及目标生成分辨率，请据此扩写为一段内容丰富、细节充分的视觉描述，以帮助文生图模型生成高质量的图片。仅输出增强后的描述，不要包含任何解释或前缀。" -%}
9
- {%- if messages[0]["role"] == "system" and messages[0]["content"] -%}
10
- {%- set sp = messages[0]["content"] -%}
11
- {%- endif -%}
12
- {{- bos_token }}{{ sp }}
13
- {% for message in messages -%}
14
- {%- if message["role"] == "user" -%}
15
- Input: {{ message["content"] }}
16
-
17
- Output:
18
- {%- elif message["role"] == "assistant" -%}
19
- {%- generation %}{{ message["content"] }}{{ eos_token }}{% endgeneration %}
20
- {%- endif -%}
21
- {%- endfor -%}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
pe/config.json DELETED
@@ -1,38 +0,0 @@
1
- {
2
- "architectures": [
3
- "Ministral3ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 1,
7
- "dtype": "bfloat16",
8
- "eos_token_id": 2,
9
- "head_dim": 128,
10
- "hidden_act": "silu",
11
- "hidden_size": 3072,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 9216,
14
- "max_position_embeddings": 262144,
15
- "model_type": "ministral3",
16
- "num_attention_heads": 32,
17
- "num_hidden_layers": 26,
18
- "num_key_value_heads": 8,
19
- "pad_token_id": 11,
20
- "rms_norm_eps": 1e-05,
21
- "rope_parameters": {
22
- "beta_fast": 32.0,
23
- "beta_slow": 1.0,
24
- "factor": 16.0,
25
- "llama_4_scaling_beta": 0.1,
26
- "mscale": 1.0,
27
- "mscale_all_dim": 1.0,
28
- "original_max_position_embeddings": 16384,
29
- "rope_theta": 1000000.0,
30
- "rope_type": "yarn",
31
- "type": "yarn"
32
- },
33
- "sliding_window": null,
34
- "tie_word_embeddings": true,
35
- "transformers_version": "5.3.0",
36
- "use_cache": true,
37
- "vocab_size": 131072
38
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
pe/generation_config.json DELETED
@@ -1,8 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 11,
6
- "transformers_version": "5.3.0",
7
- "use_cache": true
8
- }
 
 
 
 
 
 
 
 
 
pe/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f92295bf77c4b74bc5398e8761c218dddbb96108bdcfa82094439b0bdab111e2
3
- size 7663346520
 
 
 
 
pe/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:577575622324b2e099e2648be26bdeb5e5815ffe66d7004e9e3ddbf421db6bf1
3
- size 17078110
 
 
 
 
pe/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "add_prefix_space": null,
3
- "backend": "tokenizers",
4
- "bos_token": "<s>",
5
- "clean_up_tokenization_spaces": false,
6
- "eos_token": "</s>",
7
- "is_local": true,
8
- "legacy": true,
9
- "model_max_length": 1000000000000000019884624838656,
10
- "pad_token": "<pad>",
11
- "processor_class": "PixtralProcessor",
12
- "tokenizer_class": "TokenizersBackend",
13
- "unk_token": "<unk>",
14
- "use_default_system_prompt": false
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
scheduler/scheduler_config.json DELETED
@@ -1,18 +0,0 @@
1
- {
2
- "_class_name": "FlowMatchEulerDiscreteScheduler",
3
- "_diffusers_version": "0.36.0",
4
- "base_image_seq_len": 256,
5
- "base_shift": 0.5,
6
- "invert_sigmas": false,
7
- "max_image_seq_len": 4096,
8
- "max_shift": 1.15,
9
- "num_train_timesteps": 1000,
10
- "shift": 3.0,
11
- "shift_terminal": null,
12
- "stochastic_sampling": false,
13
- "time_shift_type": "exponential",
14
- "use_beta_sigmas": false,
15
- "use_dynamic_shifting": false,
16
- "use_exponential_sigmas": false,
17
- "use_karras_sigmas": false
18
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
text_encoder/config.json DELETED
@@ -1,67 +0,0 @@
1
- {
2
- "architectures": [
3
- "Mistral3Model"
4
- ],
5
- "dtype": "bfloat16",
6
- "image_token_index": 10,
7
- "model_type": "mistral3",
8
- "multimodal_projector_bias": false,
9
- "projector_hidden_act": "gelu",
10
- "spatial_merge_size": 2,
11
- "text_config": {
12
- "attention_dropout": 0.0,
13
- "bos_token_id": 1,
14
- "dtype": "bfloat16",
15
- "eos_token_id": 2,
16
- "head_dim": 128,
17
- "hidden_act": "silu",
18
- "hidden_size": 3072,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 9216,
21
- "max_position_embeddings": 262144,
22
- "model_type": "ministral3",
23
- "num_attention_heads": 32,
24
- "num_hidden_layers": 26,
25
- "num_key_value_heads": 8,
26
- "pad_token_id": 11,
27
- "rms_norm_eps": 1e-05,
28
- "rope_parameters": {
29
- "beta_fast": 32.0,
30
- "beta_slow": 1.0,
31
- "factor": 16.0,
32
- "llama_4_scaling_beta": 0.1,
33
- "mscale": 1.0,
34
- "mscale_all_dim": 1.0,
35
- "original_max_position_embeddings": 16384,
36
- "rope_theta": 1000000.0,
37
- "rope_type": "yarn",
38
- "type": "yarn"
39
- },
40
- "sliding_window": null,
41
- "tie_word_embeddings": true,
42
- "use_cache": true,
43
- "vocab_size": 131072
44
- },
45
- "tie_word_embeddings": true,
46
- "transformers_version": "5.2.0",
47
- "vision_config": {
48
- "attention_dropout": 0.0,
49
- "dtype": "bfloat16",
50
- "head_dim": 64,
51
- "hidden_act": "silu",
52
- "hidden_size": 1024,
53
- "image_size": 1540,
54
- "initializer_range": 0.02,
55
- "intermediate_size": 4096,
56
- "model_type": "pixtral",
57
- "num_attention_heads": 16,
58
- "num_channels": 3,
59
- "num_hidden_layers": 24,
60
- "patch_size": 14,
61
- "rope_parameters": {
62
- "rope_theta": 10000.0,
63
- "rope_type": "default"
64
- }
65
- },
66
- "vision_feature_layer": -1
67
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
text_encoder/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2188c5b3d759ac35e3770056153fdcb348276bd1d10f0443a60a2bdcbb6ff7b
3
- size 7698241104
 
 
 
 
tokenizer/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:577575622324b2e099e2648be26bdeb5e5815ffe66d7004e9e3ddbf421db6bf1
3
- size 17078110
 
 
 
 
tokenizer/tokenizer_config.json DELETED
@@ -1,15 +0,0 @@
1
- {
2
- "add_prefix_space": null,
3
- "backend": "tokenizers",
4
- "bos_token": "<s>",
5
- "clean_up_tokenization_spaces": false,
6
- "eos_token": "</s>",
7
- "is_local": true,
8
- "legacy": true,
9
- "model_max_length": 1000000000000000019884624838656,
10
- "pad_token": "<pad>",
11
- "processor_class": "PixtralProcessor",
12
- "tokenizer_class": "TokenizersBackend",
13
- "unk_token": "<unk>",
14
- "use_default_system_prompt": false
15
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
transformer/config.json DELETED
@@ -1,20 +0,0 @@
1
- {
2
- "_class_name": "ErnieImageTransformer2DModel",
3
- "_diffusers_version": "0.36.0",
4
- "eps": 1e-06,
5
- "ffn_hidden_size": 12288,
6
- "hidden_size": 4096,
7
- "in_channels": 128,
8
- "num_attention_heads": 32,
9
- "num_layers": 36,
10
- "out_channels": 128,
11
- "patch_size": 1,
12
- "qk_layernorm": true,
13
- "rope_axes_dim": [
14
- 32,
15
- 48,
16
- 48
17
- ],
18
- "rope_theta": 256,
19
- "text_in_dim": 3072
20
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
transformer/diffusion_pytorch_model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:57b041fdc42be778c7fd12be6514c8151a6d9a24463ae84ffc78916cc9621129
3
- size 9992362384
 
 
 
 
transformer/diffusion_pytorch_model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bb215cdcf876cb29388781e9ae53e92c2c8ff2cd06e7d86625f66ec96d24452
3
- size 6074662712
 
 
 
 
transformer/diffusion_pytorch_model.safetensors.index.json DELETED
@@ -1,416 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 16066980096
4
- },
5
- "weight_map": {
6
- "adaLN_modulation.1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
7
- "adaLN_modulation.1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
8
- "final_linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
9
- "final_linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
10
- "final_norm.linear.bias": "diffusion_pytorch_model-00002-of-00002.safetensors",
11
- "final_norm.linear.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
12
- "layers.0.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
13
- "layers.0.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
14
- "layers.0.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
15
- "layers.0.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
16
- "layers.0.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
17
- "layers.0.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
18
- "layers.0.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
19
- "layers.0.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
20
- "layers.0.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
21
- "layers.0.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
22
- "layers.0.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
23
- "layers.1.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
24
- "layers.1.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
25
- "layers.1.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
26
- "layers.1.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
27
- "layers.1.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
28
- "layers.1.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
29
- "layers.1.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
30
- "layers.1.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
31
- "layers.1.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
32
- "layers.1.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
33
- "layers.1.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
34
- "layers.10.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
35
- "layers.10.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
36
- "layers.10.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
37
- "layers.10.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
38
- "layers.10.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
39
- "layers.10.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
40
- "layers.10.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
41
- "layers.10.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
42
- "layers.10.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
43
- "layers.10.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
44
- "layers.10.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
45
- "layers.11.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
46
- "layers.11.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
47
- "layers.11.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
48
- "layers.11.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
49
- "layers.11.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
50
- "layers.11.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
51
- "layers.11.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
52
- "layers.11.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
53
- "layers.11.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
54
- "layers.11.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
55
- "layers.11.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
56
- "layers.12.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
57
- "layers.12.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
58
- "layers.12.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
59
- "layers.12.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
60
- "layers.12.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
61
- "layers.12.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
62
- "layers.12.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
63
- "layers.12.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
64
- "layers.12.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
65
- "layers.12.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
66
- "layers.12.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
67
- "layers.13.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
68
- "layers.13.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
69
- "layers.13.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
70
- "layers.13.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
71
- "layers.13.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
72
- "layers.13.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
73
- "layers.13.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
74
- "layers.13.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
75
- "layers.13.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
76
- "layers.13.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
77
- "layers.13.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
78
- "layers.14.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
79
- "layers.14.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
80
- "layers.14.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
81
- "layers.14.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
82
- "layers.14.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
83
- "layers.14.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
84
- "layers.14.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
85
- "layers.14.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
86
- "layers.14.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
87
- "layers.14.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
88
- "layers.14.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
89
- "layers.15.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
90
- "layers.15.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
91
- "layers.15.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
92
- "layers.15.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
93
- "layers.15.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
94
- "layers.15.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
95
- "layers.15.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
96
- "layers.15.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
97
- "layers.15.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
98
- "layers.15.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
99
- "layers.15.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
100
- "layers.16.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
101
- "layers.16.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
102
- "layers.16.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
103
- "layers.16.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
104
- "layers.16.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
105
- "layers.16.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
106
- "layers.16.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
107
- "layers.16.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
108
- "layers.16.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
109
- "layers.16.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
110
- "layers.16.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
111
- "layers.17.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
112
- "layers.17.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
113
- "layers.17.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
114
- "layers.17.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
115
- "layers.17.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
116
- "layers.17.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
117
- "layers.17.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
118
- "layers.17.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
119
- "layers.17.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
120
- "layers.17.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
121
- "layers.17.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
122
- "layers.18.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
123
- "layers.18.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
124
- "layers.18.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
125
- "layers.18.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
126
- "layers.18.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
127
- "layers.18.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
128
- "layers.18.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
129
- "layers.18.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
130
- "layers.18.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
131
- "layers.18.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
132
- "layers.18.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
133
- "layers.19.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
134
- "layers.19.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
135
- "layers.19.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
136
- "layers.19.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
137
- "layers.19.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
138
- "layers.19.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
139
- "layers.19.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
140
- "layers.19.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
141
- "layers.19.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
142
- "layers.19.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
143
- "layers.19.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
144
- "layers.2.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
145
- "layers.2.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
146
- "layers.2.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
147
- "layers.2.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
148
- "layers.2.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
149
- "layers.2.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
150
- "layers.2.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
151
- "layers.2.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
152
- "layers.2.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
153
- "layers.2.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
154
- "layers.2.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
155
- "layers.20.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
156
- "layers.20.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
157
- "layers.20.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
158
- "layers.20.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
159
- "layers.20.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
160
- "layers.20.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
161
- "layers.20.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
162
- "layers.20.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
163
- "layers.20.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
164
- "layers.20.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
165
- "layers.20.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
166
- "layers.21.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
167
- "layers.21.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
168
- "layers.21.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
169
- "layers.21.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
170
- "layers.21.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
171
- "layers.21.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
172
- "layers.21.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
173
- "layers.21.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
174
- "layers.21.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
175
- "layers.21.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
176
- "layers.21.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
177
- "layers.22.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
178
- "layers.22.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
179
- "layers.22.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
180
- "layers.22.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
181
- "layers.22.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
182
- "layers.22.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
183
- "layers.22.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
184
- "layers.22.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
185
- "layers.22.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
186
- "layers.22.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
187
- "layers.22.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
188
- "layers.23.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
189
- "layers.23.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
190
- "layers.23.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
191
- "layers.23.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
192
- "layers.23.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
193
- "layers.23.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
194
- "layers.23.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
195
- "layers.23.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
196
- "layers.23.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
197
- "layers.23.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
198
- "layers.23.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
199
- "layers.24.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
200
- "layers.24.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
201
- "layers.24.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
202
- "layers.24.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
203
- "layers.24.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
204
- "layers.24.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
205
- "layers.24.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
206
- "layers.24.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
207
- "layers.24.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
208
- "layers.24.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
209
- "layers.24.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
210
- "layers.25.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
211
- "layers.25.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
212
- "layers.25.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
213
- "layers.25.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
214
- "layers.25.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
215
- "layers.25.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
216
- "layers.25.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
217
- "layers.25.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
218
- "layers.25.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
219
- "layers.25.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
220
- "layers.25.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
221
- "layers.26.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
222
- "layers.26.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
223
- "layers.26.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
224
- "layers.26.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
225
- "layers.26.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
226
- "layers.26.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
227
- "layers.26.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
228
- "layers.26.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
229
- "layers.26.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
230
- "layers.26.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
231
- "layers.26.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
232
- "layers.27.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
233
- "layers.27.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
234
- "layers.27.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
235
- "layers.27.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
236
- "layers.27.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
237
- "layers.27.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
238
- "layers.27.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
239
- "layers.27.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
240
- "layers.27.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
241
- "layers.27.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
242
- "layers.27.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
243
- "layers.28.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
244
- "layers.28.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
245
- "layers.28.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
246
- "layers.28.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
247
- "layers.28.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
248
- "layers.28.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
249
- "layers.28.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
250
- "layers.28.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
251
- "layers.28.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
252
- "layers.28.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
253
- "layers.28.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
254
- "layers.29.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
255
- "layers.29.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
256
- "layers.29.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
257
- "layers.29.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
258
- "layers.29.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
259
- "layers.29.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
260
- "layers.29.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
261
- "layers.29.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
262
- "layers.29.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
263
- "layers.29.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
264
- "layers.29.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
265
- "layers.3.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
266
- "layers.3.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
267
- "layers.3.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
268
- "layers.3.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
269
- "layers.3.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
270
- "layers.3.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
271
- "layers.3.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
272
- "layers.3.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
273
- "layers.3.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
274
- "layers.3.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
275
- "layers.3.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
276
- "layers.30.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
277
- "layers.30.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
278
- "layers.30.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
279
- "layers.30.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
280
- "layers.30.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
281
- "layers.30.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
282
- "layers.30.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
283
- "layers.30.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
284
- "layers.30.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
285
- "layers.30.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
286
- "layers.30.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
287
- "layers.31.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
288
- "layers.31.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
289
- "layers.31.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
290
- "layers.31.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
291
- "layers.31.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
292
- "layers.31.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
293
- "layers.31.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
294
- "layers.31.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
295
- "layers.31.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
296
- "layers.31.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
297
- "layers.31.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
298
- "layers.32.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
299
- "layers.32.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
300
- "layers.32.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
301
- "layers.32.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
302
- "layers.32.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
303
- "layers.32.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
304
- "layers.32.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
305
- "layers.32.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
306
- "layers.32.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
307
- "layers.32.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
308
- "layers.32.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
309
- "layers.33.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
310
- "layers.33.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
311
- "layers.33.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
312
- "layers.33.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
313
- "layers.33.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
314
- "layers.33.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
315
- "layers.33.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
316
- "layers.33.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
317
- "layers.33.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
318
- "layers.33.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
319
- "layers.33.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
320
- "layers.34.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
321
- "layers.34.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
322
- "layers.34.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
323
- "layers.34.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
324
- "layers.34.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
325
- "layers.34.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
326
- "layers.34.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
327
- "layers.34.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
328
- "layers.34.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
329
- "layers.34.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
330
- "layers.34.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
331
- "layers.35.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
332
- "layers.35.adaLN_sa_ln.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
333
- "layers.35.mlp.gate_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
334
- "layers.35.mlp.linear_fc2.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
335
- "layers.35.mlp.up_proj.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
336
- "layers.35.self_attention.norm_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
337
- "layers.35.self_attention.to_k.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
338
- "layers.35.self_attention.to_out.0.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
339
- "layers.35.self_attention.norm_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
340
- "layers.35.self_attention.to_q.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
341
- "layers.35.self_attention.to_v.weight": "diffusion_pytorch_model-00002-of-00002.safetensors",
342
- "layers.4.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
343
- "layers.4.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
344
- "layers.4.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
345
- "layers.4.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
346
- "layers.4.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
347
- "layers.4.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
348
- "layers.4.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
349
- "layers.4.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
350
- "layers.4.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
351
- "layers.4.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
352
- "layers.4.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
353
- "layers.5.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
354
- "layers.5.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
355
- "layers.5.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
356
- "layers.5.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
357
- "layers.5.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
358
- "layers.5.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
359
- "layers.5.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
360
- "layers.5.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
361
- "layers.5.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
362
- "layers.5.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
363
- "layers.5.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
364
- "layers.6.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
365
- "layers.6.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
366
- "layers.6.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
367
- "layers.6.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
368
- "layers.6.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
369
- "layers.6.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
370
- "layers.6.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
371
- "layers.6.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
372
- "layers.6.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
373
- "layers.6.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
374
- "layers.6.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
375
- "layers.7.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
376
- "layers.7.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
377
- "layers.7.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
378
- "layers.7.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
379
- "layers.7.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
380
- "layers.7.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
381
- "layers.7.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
382
- "layers.7.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
383
- "layers.7.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
384
- "layers.7.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
385
- "layers.7.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
386
- "layers.8.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
387
- "layers.8.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
388
- "layers.8.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
389
- "layers.8.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
390
- "layers.8.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
391
- "layers.8.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
392
- "layers.8.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
393
- "layers.8.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
394
- "layers.8.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
395
- "layers.8.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
396
- "layers.8.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
397
- "layers.9.adaLN_mlp_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
398
- "layers.9.adaLN_sa_ln.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
399
- "layers.9.mlp.gate_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
400
- "layers.9.mlp.linear_fc2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
401
- "layers.9.mlp.up_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
402
- "layers.9.self_attention.norm_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
403
- "layers.9.self_attention.to_k.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
404
- "layers.9.self_attention.to_out.0.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
405
- "layers.9.self_attention.norm_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
406
- "layers.9.self_attention.to_q.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
407
- "layers.9.self_attention.to_v.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
408
- "text_proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
409
- "time_embedding.linear_1.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
410
- "time_embedding.linear_1.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
411
- "time_embedding.linear_2.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
412
- "time_embedding.linear_2.weight": "diffusion_pytorch_model-00001-of-00002.safetensors",
413
- "x_embedder.proj.bias": "diffusion_pytorch_model-00001-of-00002.safetensors",
414
- "x_embedder.proj.weight": "diffusion_pytorch_model-00001-of-00002.safetensors"
415
- }
416
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vae/config.json DELETED
@@ -1,40 +0,0 @@
1
- {
2
- "_class_name": "AutoencoderKLFlux2",
3
- "_diffusers_version": "0.36.0",
4
- "_name_or_path": "./weights/black-forest-labs/FLUX.2-dev/vae/",
5
- "act_fn": "silu",
6
- "batch_norm_eps": 0.0001,
7
- "batch_norm_momentum": 0.1,
8
- "block_out_channels": [
9
- 128,
10
- 256,
11
- 512,
12
- 512
13
- ],
14
- "down_block_types": [
15
- "DownEncoderBlock2D",
16
- "DownEncoderBlock2D",
17
- "DownEncoderBlock2D",
18
- "DownEncoderBlock2D"
19
- ],
20
- "force_upcast": true,
21
- "in_channels": 3,
22
- "latent_channels": 32,
23
- "layers_per_block": 2,
24
- "mid_block_add_attention": true,
25
- "norm_num_groups": 32,
26
- "out_channels": 3,
27
- "patch_size": [
28
- 2,
29
- 2
30
- ],
31
- "sample_size": 1024,
32
- "up_block_types": [
33
- "UpDecoderBlock2D",
34
- "UpDecoderBlock2D",
35
- "UpDecoderBlock2D",
36
- "UpDecoderBlock2D"
37
- ],
38
- "use_post_quant_conv": true,
39
- "use_quant_conv": true
40
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
vae/diffusion_pytorch_model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca70d2202afe6415bdbcb8793ba8cd99fd159cfe6192381504d6c4d3036e0f04
3
- size 168120878