recoilme
commited on
Commit
·
49f47c7
1
Parent(s):
e12c386
diffusers
Browse files- .gitattributes +1 -0
- datasets/alchemist/dataset_info.json +3 -47
- datasets/alchemist/state.json +3 -20
- datasets/butterfly/dataset_info.json +3 -47
- datasets/butterfly/state.json +3 -20
- scheduler/scheduler_config.json +3 -18
- text_encoder/config.json +3 -60
- unet/config.json +3 -78
- vae/config.json +3 -38
.gitattributes
CHANGED
|
@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 36 |
*.jpg filter=lfs diff=lfs merge=lfs -text
|
| 37 |
*.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
tokenizer/*.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 36 |
*.jpg filter=lfs diff=lfs merge=lfs -text
|
| 37 |
*.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
tokenizer/*.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
*.json filter=lfs diff=lfs merge=lfs -text
|
datasets/alchemist/dataset_info.json
CHANGED
|
@@ -1,47 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"features": {
|
| 5 |
-
"image_path": {
|
| 6 |
-
"dtype": "string",
|
| 7 |
-
"_type": "Value"
|
| 8 |
-
},
|
| 9 |
-
"text": {
|
| 10 |
-
"dtype": "string",
|
| 11 |
-
"_type": "Value"
|
| 12 |
-
},
|
| 13 |
-
"vae": {
|
| 14 |
-
"feature": {
|
| 15 |
-
"feature": {
|
| 16 |
-
"feature": {
|
| 17 |
-
"dtype": "float16",
|
| 18 |
-
"_type": "Value"
|
| 19 |
-
},
|
| 20 |
-
"_type": "List"
|
| 21 |
-
},
|
| 22 |
-
"_type": "List"
|
| 23 |
-
},
|
| 24 |
-
"_type": "List"
|
| 25 |
-
},
|
| 26 |
-
"embeddings": {
|
| 27 |
-
"feature": {
|
| 28 |
-
"feature": {
|
| 29 |
-
"dtype": "float32",
|
| 30 |
-
"_type": "Value"
|
| 31 |
-
},
|
| 32 |
-
"_type": "List"
|
| 33 |
-
},
|
| 34 |
-
"_type": "List"
|
| 35 |
-
},
|
| 36 |
-
"width": {
|
| 37 |
-
"dtype": "int64",
|
| 38 |
-
"_type": "Value"
|
| 39 |
-
},
|
| 40 |
-
"height": {
|
| 41 |
-
"dtype": "int64",
|
| 42 |
-
"_type": "Value"
|
| 43 |
-
}
|
| 44 |
-
},
|
| 45 |
-
"homepage": "",
|
| 46 |
-
"license": ""
|
| 47 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1033764907721e276d6b5032efdfb9479464c73dce5346e27eedc6e28ef40d6e
|
| 3 |
+
size 818
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
datasets/alchemist/state.json
CHANGED
|
@@ -1,20 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"filename": "data-00000-of-00001.arrow"
|
| 5 |
-
}
|
| 6 |
-
],
|
| 7 |
-
"_fingerprint": "81e2e22d7e730cc2",
|
| 8 |
-
"_format_columns": [
|
| 9 |
-
"image_path",
|
| 10 |
-
"text",
|
| 11 |
-
"vae",
|
| 12 |
-
"embeddings",
|
| 13 |
-
"width",
|
| 14 |
-
"height"
|
| 15 |
-
],
|
| 16 |
-
"_format_kwargs": {},
|
| 17 |
-
"_format_type": null,
|
| 18 |
-
"_output_all_columns": false,
|
| 19 |
-
"_split": null
|
| 20 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63b1be8351de9c7703925d48fad88119bf2f7cb1bed54721c94037573d6032b4
|
| 3 |
+
size 333
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
datasets/butterfly/dataset_info.json
CHANGED
|
@@ -1,47 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"features": {
|
| 5 |
-
"image_path": {
|
| 6 |
-
"dtype": "string",
|
| 7 |
-
"_type": "Value"
|
| 8 |
-
},
|
| 9 |
-
"text": {
|
| 10 |
-
"dtype": "string",
|
| 11 |
-
"_type": "Value"
|
| 12 |
-
},
|
| 13 |
-
"vae": {
|
| 14 |
-
"feature": {
|
| 15 |
-
"feature": {
|
| 16 |
-
"feature": {
|
| 17 |
-
"dtype": "float16",
|
| 18 |
-
"_type": "Value"
|
| 19 |
-
},
|
| 20 |
-
"_type": "List"
|
| 21 |
-
},
|
| 22 |
-
"_type": "List"
|
| 23 |
-
},
|
| 24 |
-
"_type": "List"
|
| 25 |
-
},
|
| 26 |
-
"embeddings": {
|
| 27 |
-
"feature": {
|
| 28 |
-
"feature": {
|
| 29 |
-
"dtype": "float32",
|
| 30 |
-
"_type": "Value"
|
| 31 |
-
},
|
| 32 |
-
"_type": "List"
|
| 33 |
-
},
|
| 34 |
-
"_type": "List"
|
| 35 |
-
},
|
| 36 |
-
"width": {
|
| 37 |
-
"dtype": "int64",
|
| 38 |
-
"_type": "Value"
|
| 39 |
-
},
|
| 40 |
-
"height": {
|
| 41 |
-
"dtype": "int64",
|
| 42 |
-
"_type": "Value"
|
| 43 |
-
}
|
| 44 |
-
},
|
| 45 |
-
"homepage": "",
|
| 46 |
-
"license": ""
|
| 47 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1033764907721e276d6b5032efdfb9479464c73dce5346e27eedc6e28ef40d6e
|
| 3 |
+
size 818
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
datasets/butterfly/state.json
CHANGED
|
@@ -1,20 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"filename": "data-00000-of-00001.arrow"
|
| 5 |
-
}
|
| 6 |
-
],
|
| 7 |
-
"_fingerprint": "23217366db2250df",
|
| 8 |
-
"_format_columns": [
|
| 9 |
-
"image_path",
|
| 10 |
-
"text",
|
| 11 |
-
"vae",
|
| 12 |
-
"embeddings",
|
| 13 |
-
"width",
|
| 14 |
-
"height"
|
| 15 |
-
],
|
| 16 |
-
"_format_kwargs": {},
|
| 17 |
-
"_format_type": null,
|
| 18 |
-
"_output_all_columns": false,
|
| 19 |
-
"_split": null
|
| 20 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5c2862bf6140b141f42cfafae0901a621cc1165286e9975d734f9ded8a8862f
|
| 3 |
+
size 333
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
scheduler/scheduler_config.json
CHANGED
|
@@ -1,18 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 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": 1.0,
|
| 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 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad559f5b938d5eac3c1f95f9d96dcfc8d0e4f9780f65755aa0d7e924c0f981c9
|
| 3 |
+
size 482
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
text_encoder/config.json
CHANGED
|
@@ -1,60 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
],
|
| 5 |
-
"attention_bias": false,
|
| 6 |
-
"attention_dropout": 0.0,
|
| 7 |
-
"bos_token_id": 151643,
|
| 8 |
-
"dtype": "float16",
|
| 9 |
-
"eos_token_id": 151643,
|
| 10 |
-
"head_dim": 128,
|
| 11 |
-
"hidden_act": "silu",
|
| 12 |
-
"hidden_size": 1024,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 3072,
|
| 15 |
-
"layer_types": [
|
| 16 |
-
"full_attention",
|
| 17 |
-
"full_attention",
|
| 18 |
-
"full_attention",
|
| 19 |
-
"full_attention",
|
| 20 |
-
"full_attention",
|
| 21 |
-
"full_attention",
|
| 22 |
-
"full_attention",
|
| 23 |
-
"full_attention",
|
| 24 |
-
"full_attention",
|
| 25 |
-
"full_attention",
|
| 26 |
-
"full_attention",
|
| 27 |
-
"full_attention",
|
| 28 |
-
"full_attention",
|
| 29 |
-
"full_attention",
|
| 30 |
-
"full_attention",
|
| 31 |
-
"full_attention",
|
| 32 |
-
"full_attention",
|
| 33 |
-
"full_attention",
|
| 34 |
-
"full_attention",
|
| 35 |
-
"full_attention",
|
| 36 |
-
"full_attention",
|
| 37 |
-
"full_attention",
|
| 38 |
-
"full_attention",
|
| 39 |
-
"full_attention",
|
| 40 |
-
"full_attention",
|
| 41 |
-
"full_attention",
|
| 42 |
-
"full_attention",
|
| 43 |
-
"full_attention"
|
| 44 |
-
],
|
| 45 |
-
"max_position_embeddings": 32768,
|
| 46 |
-
"max_window_layers": 28,
|
| 47 |
-
"model_type": "qwen3",
|
| 48 |
-
"num_attention_heads": 16,
|
| 49 |
-
"num_hidden_layers": 28,
|
| 50 |
-
"num_key_value_heads": 8,
|
| 51 |
-
"rms_norm_eps": 1e-06,
|
| 52 |
-
"rope_scaling": null,
|
| 53 |
-
"rope_theta": 1000000,
|
| 54 |
-
"sliding_window": null,
|
| 55 |
-
"tie_word_embeddings": true,
|
| 56 |
-
"transformers_version": "4.56.2",
|
| 57 |
-
"use_cache": true,
|
| 58 |
-
"use_sliding_window": false,
|
| 59 |
-
"vocab_size": 151669
|
| 60 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c0adcad14f37d1cac621fa7983257dd0e0bfeeebb6e123c3998fc03dceac34a
|
| 3 |
+
size 1353
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
unet/config.json
CHANGED
|
@@ -1,78 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"_name_or_path": "/workspace/sdxs3d",
|
| 5 |
-
"act_fn": "silu",
|
| 6 |
-
"addition_embed_type": null,
|
| 7 |
-
"addition_embed_type_num_heads": 64,
|
| 8 |
-
"addition_time_embed_dim": null,
|
| 9 |
-
"attention_head_dim": [
|
| 10 |
-
4,
|
| 11 |
-
8,
|
| 12 |
-
16,
|
| 13 |
-
16
|
| 14 |
-
],
|
| 15 |
-
"attention_type": "default",
|
| 16 |
-
"block_out_channels": [
|
| 17 |
-
256,
|
| 18 |
-
512,
|
| 19 |
-
1024,
|
| 20 |
-
1024
|
| 21 |
-
],
|
| 22 |
-
"center_input_sample": false,
|
| 23 |
-
"class_embed_type": null,
|
| 24 |
-
"class_embeddings_concat": false,
|
| 25 |
-
"conv_in_kernel": 3,
|
| 26 |
-
"conv_out_kernel": 3,
|
| 27 |
-
"cross_attention_dim": 1024,
|
| 28 |
-
"cross_attention_norm": null,
|
| 29 |
-
"down_block_types": [
|
| 30 |
-
"DownBlock2D",
|
| 31 |
-
"CrossAttnDownBlock2D",
|
| 32 |
-
"CrossAttnDownBlock2D",
|
| 33 |
-
"CrossAttnDownBlock2D"
|
| 34 |
-
],
|
| 35 |
-
"downsample_padding": 1,
|
| 36 |
-
"dropout": 0.0,
|
| 37 |
-
"dual_cross_attention": false,
|
| 38 |
-
"encoder_hid_dim": null,
|
| 39 |
-
"encoder_hid_dim_type": null,
|
| 40 |
-
"flip_sin_to_cos": true,
|
| 41 |
-
"freq_shift": 0,
|
| 42 |
-
"in_channels": 16,
|
| 43 |
-
"layers_per_block": 2,
|
| 44 |
-
"mid_block_only_cross_attention": null,
|
| 45 |
-
"mid_block_scale_factor": 1,
|
| 46 |
-
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 47 |
-
"norm_eps": 1e-05,
|
| 48 |
-
"norm_num_groups": 32,
|
| 49 |
-
"num_attention_heads": null,
|
| 50 |
-
"num_class_embeds": null,
|
| 51 |
-
"only_cross_attention": false,
|
| 52 |
-
"out_channels": 16,
|
| 53 |
-
"projection_class_embeddings_input_dim": null,
|
| 54 |
-
"resnet_out_scale_factor": 1.0,
|
| 55 |
-
"resnet_skip_time_act": false,
|
| 56 |
-
"resnet_time_scale_shift": "default",
|
| 57 |
-
"reverse_transformer_layers_per_block": null,
|
| 58 |
-
"sample_size": null,
|
| 59 |
-
"time_cond_proj_dim": null,
|
| 60 |
-
"time_embedding_act_fn": null,
|
| 61 |
-
"time_embedding_dim": null,
|
| 62 |
-
"time_embedding_type": "positional",
|
| 63 |
-
"timestep_post_act": null,
|
| 64 |
-
"transformer_layers_per_block": [
|
| 65 |
-
1,
|
| 66 |
-
1,
|
| 67 |
-
1,
|
| 68 |
-
8
|
| 69 |
-
],
|
| 70 |
-
"up_block_types": [
|
| 71 |
-
"CrossAttnUpBlock2D",
|
| 72 |
-
"CrossAttnUpBlock2D",
|
| 73 |
-
"CrossAttnUpBlock2D",
|
| 74 |
-
"UpBlock2D"
|
| 75 |
-
],
|
| 76 |
-
"upcast_attention": false,
|
| 77 |
-
"use_linear_projection": true
|
| 78 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afc06beff07034f0ce9f671c83222e7f78eedc3b3ce93293143accdebef1b111
|
| 3 |
+
size 1887
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vae/config.json
CHANGED
|
@@ -1,38 +1,3 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
| 4 |
-
"_name_or_path": "AiArtLab/simplevae",
|
| 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": 16,
|
| 21 |
-
"latents_mean": null,
|
| 22 |
-
"latents_std": null,
|
| 23 |
-
"layers_per_block": 2,
|
| 24 |
-
"mid_block_add_attention": true,
|
| 25 |
-
"norm_num_groups": 32,
|
| 26 |
-
"out_channels": 3,
|
| 27 |
-
"sample_size": 1024,
|
| 28 |
-
"scaling_factor": 1.0,
|
| 29 |
-
"shift_factor": 0,
|
| 30 |
-
"up_block_types": [
|
| 31 |
-
"UpDecoderBlock2D",
|
| 32 |
-
"UpDecoderBlock2D",
|
| 33 |
-
"UpDecoderBlock2D",
|
| 34 |
-
"UpDecoderBlock2D"
|
| 35 |
-
],
|
| 36 |
-
"use_post_quant_conv": true,
|
| 37 |
-
"use_quant_conv": true
|
| 38 |
-
}
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca78c49c02cf8afd8f022b99418bec3e4da9882cfed036c3664897af6d4589f0
|
| 3 |
+
size 801
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|