briannlongzhao
commited on
Commit
•
b5989c5
1
Parent(s):
e4e6945
End of training
Browse files- README.md +17 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/pytorch_model.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-1500/optimizer.bin +3 -0
- checkpoint-1500/pytorch_model.bin +3 -0
- checkpoint-1500/random_states_0.pkl +3 -0
- checkpoint-1500/scheduler.bin +3 -0
- checkpoint-500/optimizer.bin +3 -0
- checkpoint-500/pytorch_model.bin +3 -0
- checkpoint-500/random_states_0.pkl +3 -0
- checkpoint-500/scheduler.bin +3 -0
- feature_extractor/preprocessor_config.json +28 -0
- learned_embeds-steps-1000.safetensors +3 -0
- learned_embeds-steps-1500.safetensors +3 -0
- learned_embeds-steps-500.safetensors +3 -0
- learned_embeds.safetensors +3 -0
- logs/textual_inversion/1700042098.0703492/events.out.tfevents.1700042098.GCRAZGDL1730.979430.1 +3 -0
- logs/textual_inversion/1700042098.9015002/hparams.yml +47 -0
- logs/textual_inversion/events.out.tfevents.1700042097.GCRAZGDL1730.979430.0 +3 -0
- model_index.json +34 -0
- scheduler/scheduler_config.json +20 -0
- text_encoder/config.json +25 -0
- text_encoder/model.safetensors +3 -0
- tokenizer/added_tokens.json +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +24 -0
- tokenizer/tokenizer_config.json +46 -0
- tokenizer/vocab.json +0 -0
- unet/config.json +73 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +32 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
license: creativeml-openrail-m
|
4 |
+
base_model: stabilityai/stable-diffusion-2-1
|
5 |
+
tags:
|
6 |
+
- stable-diffusion
|
7 |
+
- stable-diffusion-diffusers
|
8 |
+
- text-to-image
|
9 |
+
- diffusers
|
10 |
+
- textual_inversion
|
11 |
+
inference: true
|
12 |
+
---
|
13 |
+
|
14 |
+
# Textual inversion text2image fine-tuning - briannlongzhao/dog_textual_inversion
|
15 |
+
These are textual inversion adaption weights for stabilityai/stable-diffusion-2-1. You can find some example images in the following.
|
16 |
+
|
17 |
+
|
checkpoint-1000/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6648cca7df5545b7b9ca0d2145f525536e4bd659458609add63f77026de1ce78
|
3 |
+
size 404760546
|
checkpoint-1000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65e62d94e332ccc76d14615292a38b30613f69916c051b78bb340b598f8cee53
|
3 |
+
size 1361701402
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:604e8519f1c4304747b89c2f6fa41a5e5ed3b7099dec29db071bac04b8efee5c
|
3 |
+
size 14408
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d66a1efc9a74a35390e8502cf42d7f477f4c271f1b07bfd430322ce244dc1bec
|
3 |
+
size 1000
|
checkpoint-1500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a3bad2d8c71be651cd5c876ec6defa4a19f517967261f18ba3005791c301974
|
3 |
+
size 404760546
|
checkpoint-1500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a46d0f09dc9903cdc304e92bc4314ea1db816c5bbd5c0dc8ca0c4eeb842dc1c
|
3 |
+
size 1361701402
|
checkpoint-1500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:779c625a9171d7ae34ad53130949b5b58f2f5201c0d620353e6c225c5ea74865
|
3 |
+
size 14408
|
checkpoint-1500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e09a6100ab78b2a1c300cd551b39a706e68bf17c9eb4cf52692d5dc017e9b0e2
|
3 |
+
size 1000
|
checkpoint-500/optimizer.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe6bcc06f746d7d2bea6acd8be9c21f7a8caef5664f8ed4f9d21e8ecf2019734
|
3 |
+
size 404760546
|
checkpoint-500/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53e5712c4c4034686eacfdf43c0b19ecc8a90075cc2be2c6acfecb2401d278c1
|
3 |
+
size 1361701402
|
checkpoint-500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c2095e52f4676f37ac8bf17ea01b8d287dd311d360bf9717aca727b0b515c06
|
3 |
+
size 14408
|
checkpoint-500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:722c61c11fb8622bf5d94fd1a8f787cb48cf02fccf61cccf4bbeae81102e5de2
|
3 |
+
size 1000
|
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_convert_rgb": true,
|
8 |
+
"do_normalize": true,
|
9 |
+
"do_rescale": true,
|
10 |
+
"do_resize": true,
|
11 |
+
"feature_extractor_type": "CLIPFeatureExtractor",
|
12 |
+
"image_mean": [
|
13 |
+
0.48145466,
|
14 |
+
0.4578275,
|
15 |
+
0.40821073
|
16 |
+
],
|
17 |
+
"image_processor_type": "CLIPImageProcessor",
|
18 |
+
"image_std": [
|
19 |
+
0.26862954,
|
20 |
+
0.26130258,
|
21 |
+
0.27577711
|
22 |
+
],
|
23 |
+
"resample": 3,
|
24 |
+
"rescale_factor": 0.00392156862745098,
|
25 |
+
"size": {
|
26 |
+
"shortest_edge": 224
|
27 |
+
}
|
28 |
+
}
|
learned_embeds-steps-1000.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2efeb00146d3b6b77b2f3f43d00119244c1f871ecb39521a89c61d05270acdb0
|
3 |
+
size 4208
|
learned_embeds-steps-1500.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95601aed87eb2ada11701d3c16be6785dd955194f335d89af92d02334b8602ce
|
3 |
+
size 4208
|
learned_embeds-steps-500.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46b2dac039ce735bcb85270b3083b02f85fb0df29196330bd369707f0f11cda9
|
3 |
+
size 4208
|
learned_embeds.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:95601aed87eb2ada11701d3c16be6785dd955194f335d89af92d02334b8602ce
|
3 |
+
size 4208
|
logs/textual_inversion/1700042098.0703492/events.out.tfevents.1700042098.GCRAZGDL1730.979430.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3310a8decd191a7722de44856f1d9bb17f4eb643e76ea0b3b4efd984a143335
|
3 |
+
size 2401
|
logs/textual_inversion/1700042098.9015002/hparams.yml
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
adam_beta1: 0.9
|
2 |
+
adam_beta2: 0.999
|
3 |
+
adam_epsilon: 1.0e-08
|
4 |
+
adam_weight_decay: 0.01
|
5 |
+
allow_tf32: false
|
6 |
+
center_crop: false
|
7 |
+
checkpointing_steps: 500
|
8 |
+
checkpoints_total_limit: null
|
9 |
+
dataloader_num_workers: 0
|
10 |
+
enable_xformers_memory_efficient_attention: true
|
11 |
+
gradient_accumulation_steps: 4
|
12 |
+
gradient_checkpointing: false
|
13 |
+
hub_model_id: null
|
14 |
+
hub_token: null
|
15 |
+
initializer_token: dog
|
16 |
+
learnable_property: object
|
17 |
+
learning_rate: 0.008
|
18 |
+
local_rank: -1
|
19 |
+
logging_dir: logs
|
20 |
+
lr_num_cycles: 1
|
21 |
+
lr_scheduler: constant
|
22 |
+
lr_warmup_steps: 0
|
23 |
+
max_train_steps: 1500
|
24 |
+
mixed_precision: bf16
|
25 |
+
no_safe_serialization: false
|
26 |
+
num_train_epochs: 35
|
27 |
+
num_validation_images: 4
|
28 |
+
num_vectors: 1
|
29 |
+
output_dir: /home/v-enlongzhao/sdcoop-images/models/dog_textual_inversion
|
30 |
+
placeholder_token: <dog>
|
31 |
+
pretrained_model_name_or_path: stabilityai/stable-diffusion-2-1
|
32 |
+
push_to_hub: true
|
33 |
+
repeats: 100
|
34 |
+
report_to: tensorboard
|
35 |
+
resolution: 768
|
36 |
+
resume_from_checkpoint: null
|
37 |
+
revision: null
|
38 |
+
save_as_full_pipeline: false
|
39 |
+
save_steps: 500
|
40 |
+
scale_lr: true
|
41 |
+
seed: null
|
42 |
+
tokenizer_name: null
|
43 |
+
train_batch_size: 4
|
44 |
+
train_data_dir: /home/v-enlongzhao/sdcoop-images/images/dog
|
45 |
+
validation_epochs: null
|
46 |
+
validation_prompt: null
|
47 |
+
validation_steps: 100
|
logs/textual_inversion/events.out.tfevents.1700042097.GCRAZGDL1730.979430.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e5dc29f705ea64236daf5e61b26dfa15751ca9995c9640346a5597c052827cd
|
3 |
+
size 500202
|
model_index.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
5 |
+
"feature_extractor": [
|
6 |
+
"transformers",
|
7 |
+
"CLIPImageProcessor"
|
8 |
+
],
|
9 |
+
"requires_safety_checker": false,
|
10 |
+
"safety_checker": [
|
11 |
+
null,
|
12 |
+
null
|
13 |
+
],
|
14 |
+
"scheduler": [
|
15 |
+
"diffusers",
|
16 |
+
"DDIMScheduler"
|
17 |
+
],
|
18 |
+
"text_encoder": [
|
19 |
+
"transformers",
|
20 |
+
"CLIPTextModel"
|
21 |
+
],
|
22 |
+
"tokenizer": [
|
23 |
+
"transformers",
|
24 |
+
"CLIPTokenizer"
|
25 |
+
],
|
26 |
+
"unet": [
|
27 |
+
"diffusers",
|
28 |
+
"UNet2DConditionModel"
|
29 |
+
],
|
30 |
+
"vae": [
|
31 |
+
"diffusers",
|
32 |
+
"AutoencoderKL"
|
33 |
+
]
|
34 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDIMScheduler",
|
3 |
+
"_diffusers_version": "0.22.0.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 |
+
"skip_prk_steps": true,
|
16 |
+
"steps_offset": 1,
|
17 |
+
"thresholding": false,
|
18 |
+
"timestep_spacing": "leading",
|
19 |
+
"trained_betas": null
|
20 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
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": "gelu",
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 23,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.34.1",
|
24 |
+
"vocab_size": 49409
|
25 |
+
}
|
text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee559de46606c370461c527d688e6d088a4e29735b758d3ec16493451a86f4eb
|
3 |
+
size 1361600400
|
tokenizer/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<dog>": 49408
|
3 |
+
}
|
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 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"49408": {
|
29 |
+
"content": "<dog>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
}
|
36 |
+
},
|
37 |
+
"bos_token": "<|startoftext|>",
|
38 |
+
"clean_up_tokenization_spaces": true,
|
39 |
+
"do_lower_case": true,
|
40 |
+
"eos_token": "<|endoftext|>",
|
41 |
+
"errors": "replace",
|
42 |
+
"model_max_length": 77,
|
43 |
+
"pad_token": "!",
|
44 |
+
"tokenizer_class": "CLIPTokenizer",
|
45 |
+
"unk_token": "<|endoftext|>"
|
46 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
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 |
+
5,
|
11 |
+
10,
|
12 |
+
20,
|
13 |
+
20
|
14 |
+
],
|
15 |
+
"attention_type": "default",
|
16 |
+
"block_out_channels": [
|
17 |
+
320,
|
18 |
+
640,
|
19 |
+
1280,
|
20 |
+
1280
|
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 |
+
"CrossAttnDownBlock2D",
|
31 |
+
"CrossAttnDownBlock2D",
|
32 |
+
"CrossAttnDownBlock2D",
|
33 |
+
"DownBlock2D"
|
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": 4,
|
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": 4,
|
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": 96,
|
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": 1,
|
65 |
+
"up_block_types": [
|
66 |
+
"UpBlock2D",
|
67 |
+
"CrossAttnUpBlock2D",
|
68 |
+
"CrossAttnUpBlock2D",
|
69 |
+
"CrossAttnUpBlock2D"
|
70 |
+
],
|
71 |
+
"upcast_attention": true,
|
72 |
+
"use_linear_projection": true
|
73 |
+
}
|
unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fef0a55750983a09b1e01ad2d64c99cfe9cae70ef1c27d07435785e59c0ff649
|
3 |
+
size 1731905416
|
vae/config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.22.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
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": true,
|
19 |
+
"in_channels": 3,
|
20 |
+
"latent_channels": 4,
|
21 |
+
"layers_per_block": 2,
|
22 |
+
"norm_num_groups": 32,
|
23 |
+
"out_channels": 3,
|
24 |
+
"sample_size": 768,
|
25 |
+
"scaling_factor": 0.18215,
|
26 |
+
"up_block_types": [
|
27 |
+
"UpDecoderBlock2D",
|
28 |
+
"UpDecoderBlock2D",
|
29 |
+
"UpDecoderBlock2D",
|
30 |
+
"UpDecoderBlock2D"
|
31 |
+
]
|
32 |
+
}
|
vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d0c34f57abe50f323040f2366c8e22b941068dcdf53c8eb1d6fafb838afecb7
|
3 |
+
size 167335590
|