Upload 18 files
Browse files- model_index.json +33 -0
- scheduler/scheduler_config.json +21 -0
- text_encoder/config.json +25 -0
- text_encoder/pytorch_model.bin +3 -0
- text_encoder_2/config.json +25 -0
- text_encoder_2/pytorch_model.bin +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +30 -0
- tokenizer/tokenizer_config.json +30 -0
- tokenizer/vocab.json +0 -0
- tokenizer_2/merges.txt +0 -0
- tokenizer_2/special_tokens_map.json +30 -0
- tokenizer_2/tokenizer_config.json +38 -0
- tokenizer_2/vocab.json +0 -0
- unet/config.json +45 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +37 -0
- vae/diffusion_pytorch_model.bin +3 -0
model_index.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "FluxDiffPipeline",
|
3 |
+
"_diffusers_version": "0.29.2",
|
4 |
+
"_name_or_path": "FluxDiff",
|
5 |
+
"scheduler": [
|
6 |
+
"diffusers",
|
7 |
+
"DDIMScheduler"
|
8 |
+
],
|
9 |
+
"text_encoder": [
|
10 |
+
"transformers",
|
11 |
+
"CLIPTextModel"
|
12 |
+
],
|
13 |
+
"text_encoder_2": [
|
14 |
+
"transformers",
|
15 |
+
"CLIPTextModelWithProjection"
|
16 |
+
],
|
17 |
+
"tokenizer": [
|
18 |
+
"transformers",
|
19 |
+
"CLIPTokenizer"
|
20 |
+
],
|
21 |
+
"tokenizer_2": [
|
22 |
+
"transformers",
|
23 |
+
"CLIPTokenizer"
|
24 |
+
],
|
25 |
+
"unet": [
|
26 |
+
"models.unet",
|
27 |
+
"FluxDiff"
|
28 |
+
],
|
29 |
+
"vae": [
|
30 |
+
"diffusers",
|
31 |
+
"AutoencoderKL"
|
32 |
+
]
|
33 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDIMScheduler",
|
3 |
+
"_diffusers_version": "0.29.2",
|
4 |
+
"algorithm_type": "sde-dpmsolver++",
|
5 |
+
"beta_end": 0.014,
|
6 |
+
"beta_schedule": "scaled_linear",
|
7 |
+
"beta_start": 0.00082,
|
8 |
+
"clip_sample": false,
|
9 |
+
"clip_sample_range": 1.0,
|
10 |
+
"dynamic_thresholding_ratio": 0.995,
|
11 |
+
"num_train_timesteps": 1000,
|
12 |
+
"prediction_type": "epsilon",
|
13 |
+
"rescale_betas_zero_snr": false,
|
14 |
+
"sample_max_value": 1.0,
|
15 |
+
"set_alpha_to_one": false,
|
16 |
+
"skip_prk_steps": true,
|
17 |
+
"steps_offset": 1,
|
18 |
+
"thresholding": false,
|
19 |
+
"timestep_spacing": "leading",
|
20 |
+
"trained_betas": null
|
21 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FluxDiff",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "quick_gelu",
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 768,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.42.3",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58a75e6988b535f0cab27e40cad32ea8f93c0dfcf28771d156c292799e779c1a
|
3 |
+
size 492309274
|
text_encoder_2/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FluxDiff",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModelWithProjection"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_size": 1280,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5120,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 20,
|
19 |
+
"num_hidden_layers": 32,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 1280,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.42.3",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
text_encoder_2/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c08d9cc89dbda9abd153c510be1196dbfe9aeaa8ca6345442a5de130240622e
|
3 |
+
size 2778817374
|
tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"49406": {
|
5 |
+
"content": "<|startoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49407": {
|
13 |
+
"content": "<|endoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
}
|
20 |
+
},
|
21 |
+
"bos_token": "<|startoftext|>",
|
22 |
+
"clean_up_tokenization_spaces": true,
|
23 |
+
"do_lower_case": true,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 77,
|
27 |
+
"pad_token": "<|endoftext|>",
|
28 |
+
"tokenizer_class": "CLIPTokenizer",
|
29 |
+
"unk_token": "<|endoftext|>"
|
30 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_2/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_2/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "!",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer_2/tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "!",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"49406": {
|
13 |
+
"content": "<|startoftext|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"49407": {
|
21 |
+
"content": "<|endoftext|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"bos_token": "<|startoftext|>",
|
30 |
+
"clean_up_tokenization_spaces": true,
|
31 |
+
"do_lower_case": true,
|
32 |
+
"eos_token": "<|endoftext|>",
|
33 |
+
"errors": "replace",
|
34 |
+
"model_max_length": 77,
|
35 |
+
"pad_token": "!",
|
36 |
+
"tokenizer_class": "CLIPTokenizer",
|
37 |
+
"unk_token": "<|endoftext|>"
|
38 |
+
}
|
tokenizer_2/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "FluxDiff",
|
3 |
+
"_diffusers_version": "0.29.2",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"addition_time_embed_dim": 256,
|
6 |
+
"attention_head_dim": 64,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280
|
11 |
+
],
|
12 |
+
"cross_attention_dim": 2048,
|
13 |
+
"down_block_types": [
|
14 |
+
"DownBlock3D",
|
15 |
+
"CrossAttnDownBlock3D",
|
16 |
+
"CrossAttnDownBlock3D"
|
17 |
+
],
|
18 |
+
"downsample_padding": 1,
|
19 |
+
"flip_sin_to_cos": true,
|
20 |
+
"freq_shift": 0,
|
21 |
+
"in_channels": 4,
|
22 |
+
"layers_per_block": 2,
|
23 |
+
"mid_block_scale_factor": 1,
|
24 |
+
"norm_eps": 1e-05,
|
25 |
+
"norm_num_groups": 32,
|
26 |
+
"out_channels": 4,
|
27 |
+
"projection_class_embeddings_input_dim": 2816,
|
28 |
+
"sample_size": 128,
|
29 |
+
"temporal_layers_per_block": [
|
30 |
+
2,
|
31 |
+
2,
|
32 |
+
2
|
33 |
+
],
|
34 |
+
"transformer_layers_per_block": [
|
35 |
+
1,
|
36 |
+
2,
|
37 |
+
10
|
38 |
+
],
|
39 |
+
"up_block_types": [
|
40 |
+
"CrossAttnUpBlock3D",
|
41 |
+
"CrossAttnUpBlock3D",
|
42 |
+
"UpBlock3D"
|
43 |
+
],
|
44 |
+
"upcast_attention": false
|
45 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:748431a0bebfbcb8db564afd4d32ea0cbba56dc40a287e7be5cece89cd6c07e8
|
3 |
+
size 16845349880
|
vae/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "FluxDiff",
|
3 |
+
"_class_name": "AutoencoderKL",
|
4 |
+
"_diffusers_version": "0.29.2",
|
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": false,
|
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": 512,
|
27 |
+
"scaling_factor": 0.13025,
|
28 |
+
"shift_factor": null,
|
29 |
+
"up_block_types": [
|
30 |
+
"UpDecoderBlock2D",
|
31 |
+
"UpDecoderBlock2D",
|
32 |
+
"UpDecoderBlock2D",
|
33 |
+
"UpDecoderBlock2D"
|
34 |
+
],
|
35 |
+
"use_post_quant_conv": true,
|
36 |
+
"use_quant_conv": true
|
37 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d1df5e83ec9f145cfd08787ace533a16a039cec9e82b18918d695abd586f911
|
3 |
+
size 334702018
|