c6817101f1a0b36681480d4dd510c6be54f4e35d1d5e8eaf10f55d989261209b
Browse files- README.md +66 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-1000/unet/config.json +68 -0
- checkpoint-1000/unet_ema/config.json +75 -0
- checkpoint-10000/random_states_0.pkl +3 -0
- checkpoint-10000/scaler.pt +3 -0
- checkpoint-10000/scheduler.bin +3 -0
- checkpoint-10000/unet/config.json +68 -0
- checkpoint-10000/unet_ema/config.json +75 -0
- checkpoint-10500/random_states_0.pkl +3 -0
- checkpoint-10500/scaler.pt +3 -0
- checkpoint-10500/scheduler.bin +3 -0
- checkpoint-10500/unet/config.json +68 -0
- checkpoint-10500/unet_ema/config.json +75 -0
- checkpoint-11000/random_states_0.pkl +3 -0
- checkpoint-11000/scaler.pt +3 -0
- checkpoint-11000/scheduler.bin +3 -0
- checkpoint-11000/unet/config.json +68 -0
- checkpoint-11000/unet_ema/config.json +75 -0
- checkpoint-11500/random_states_0.pkl +3 -0
- checkpoint-11500/scaler.pt +3 -0
- checkpoint-11500/scheduler.bin +3 -0
- checkpoint-11500/unet/config.json +68 -0
- checkpoint-11500/unet_ema/config.json +75 -0
- checkpoint-12000/random_states_0.pkl +3 -0
- checkpoint-12000/scaler.pt +3 -0
- checkpoint-12000/scheduler.bin +3 -0
- checkpoint-12000/unet/config.json +68 -0
- checkpoint-12000/unet_ema/config.json +75 -0
- checkpoint-12500/random_states_0.pkl +3 -0
- checkpoint-12500/scaler.pt +3 -0
- checkpoint-12500/scheduler.bin +3 -0
- checkpoint-12500/unet/config.json +68 -0
- checkpoint-12500/unet_ema/config.json +75 -0
- checkpoint-13000/random_states_0.pkl +3 -0
- checkpoint-13000/scaler.pt +3 -0
- checkpoint-13000/scheduler.bin +3 -0
- checkpoint-13000/unet/config.json +68 -0
- checkpoint-13000/unet_ema/config.json +75 -0
- checkpoint-13500/random_states_0.pkl +3 -0
- checkpoint-13500/scaler.pt +3 -0
- checkpoint-13500/scheduler.bin +3 -0
- checkpoint-13500/unet/config.json +68 -0
- checkpoint-13500/unet_ema/config.json +75 -0
- checkpoint-14000/random_states_0.pkl +3 -0
- checkpoint-14000/scaler.pt +3 -0
- checkpoint-14000/scheduler.bin +3 -0
- checkpoint-14000/unet/config.json +68 -0
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: runwayml/stable-diffusion-v1-5
|
3 |
+
library_name: diffusers
|
4 |
+
license: creativeml-openrail-m
|
5 |
+
tags:
|
6 |
+
- stable-diffusion
|
7 |
+
- stable-diffusion-diffusers
|
8 |
+
- text-to-image
|
9 |
+
- diffusers
|
10 |
+
- diffusers-training
|
11 |
+
inference: true
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
|
18 |
+
# Text-to-image finetuning - spockren/sd-naruto-model
|
19 |
+
|
20 |
+
This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **lambdalabs/naruto-blip-captions** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['A <cat-toy> backpack']:
|
21 |
+
|
22 |
+
![val_imgs_grid](./val_imgs_grid.png)
|
23 |
+
|
24 |
+
|
25 |
+
## Pipeline usage
|
26 |
+
|
27 |
+
You can use the pipeline like so:
|
28 |
+
|
29 |
+
```python
|
30 |
+
from diffusers import DiffusionPipeline
|
31 |
+
import torch
|
32 |
+
|
33 |
+
pipeline = DiffusionPipeline.from_pretrained("spockren/sd-naruto-model", torch_dtype=torch.float16)
|
34 |
+
prompt = "A <cat-toy> backpack"
|
35 |
+
image = pipeline(prompt).images[0]
|
36 |
+
image.save("my_image.png")
|
37 |
+
```
|
38 |
+
|
39 |
+
## Training info
|
40 |
+
|
41 |
+
These are the key hyperparameters used during training:
|
42 |
+
|
43 |
+
* Epochs: 50
|
44 |
+
* Learning rate: 1e-05
|
45 |
+
* Batch size: 1
|
46 |
+
* Gradient accumulation steps: 4
|
47 |
+
* Image resolution: 512
|
48 |
+
* Mixed-precision: fp16
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
## Intended uses & limitations
|
53 |
+
|
54 |
+
#### How to use
|
55 |
+
|
56 |
+
```python
|
57 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
58 |
+
```
|
59 |
+
|
60 |
+
#### Limitations and bias
|
61 |
+
|
62 |
+
[TODO: provide examples of latent issues and potential remediations]
|
63 |
+
|
64 |
+
## Training details
|
65 |
+
|
66 |
+
[TODO: describe the data used to train the model]
|
checkpoint-1000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e46791f7847fcb5e901175b84796c0ae028510df22f7cc33e70c03c31b3b0c4
|
3 |
+
size 14344
|
checkpoint-1000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d8fdcd0311eba9854fff738038ed4c1a269832665b4d88ba4e4e3d02a1a7e0e
|
3 |
+
size 988
|
checkpoint-1000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d16ae9dedf4c45ceadc467593037d83423677715e75ab402a9f44aa81de9b84
|
3 |
+
size 1000
|
checkpoint-1000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-1000/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 1000,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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": 64,
|
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": false,
|
72 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-10000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5311f11d1efb932747b4c168ef571eb9ab476cd29363ea17702d349cb9c03089
|
3 |
+
size 14344
|
checkpoint-10000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d49367aa0f19981d0484e3ef5c1b009e6bdd8e5c0d8ef08f2f8d235b9f843816
|
3 |
+
size 988
|
checkpoint-10000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d31ad9a5150e341b638f838a47b3cb3db0d48efa493bcc8d1f8bf787b2c8cee3
|
3 |
+
size 1000
|
checkpoint-10000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "sd-naruto-model/checkpoint-1500",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-10000/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 8500,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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": 64,
|
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": false,
|
72 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-10500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daa8cfe5a197e48a49eb89fb9daa1a14fe9994fae80b276e8b05a3412f1ab092
|
3 |
+
size 14344
|
checkpoint-10500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01779ab2347be8e591753bc4549de9a4488b45e647b2f7921c9e29c49b9601a9
|
3 |
+
size 988
|
checkpoint-10500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94d68e9fa853ae093658f50590cc9c32d2da56551802d5c8ad20ebcaf7c6eac6
|
3 |
+
size 1000
|
checkpoint-10500/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "sd-naruto-model/checkpoint-1500",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-10500/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 9000,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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": 64,
|
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": false,
|
72 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-11000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5e3cc475c1662cad811e63e5853647790a7a87c0a82815b9249899b6b08ca9b
|
3 |
+
size 14344
|
checkpoint-11000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e21dabb36dbda24392f0722ce6e2b2605bd46104c3d4ec1d1531ebe03789c49
|
3 |
+
size 988
|
checkpoint-11000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7ba806b28f71e1e1cf1d42195652aa3e74d3e313c111b119d860e4f1aee287f
|
3 |
+
size 1000
|
checkpoint-11000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "sd-naruto-model/checkpoint-1500",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-11000/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 9500,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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": 64,
|
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": false,
|
72 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-11500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fe1d838902acc468366e6a9f7eb3f722a3553b09ff940b0cfa18d6e8032ff9e
|
3 |
+
size 14344
|
checkpoint-11500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:171482665d2dd196ceb9bb07828e79f3031503983fba849e0e18c7bb877dd4ec
|
3 |
+
size 988
|
checkpoint-11500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7b2247bda89df10af46d8fc9946fb5ac6444c073272d5755453a114baf37790
|
3 |
+
size 1000
|
checkpoint-11500/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "sd-naruto-model/checkpoint-1500",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-11500/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 10000,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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": 64,
|
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": false,
|
72 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-12000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44950f6c633f8e23fc24518b42df6aebda8aa0e9fdbc43c8b56e028672297074
|
3 |
+
size 14344
|
checkpoint-12000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d1f9d6a63312bf6188d8844a7d621f2ecda20b6c0aee9e19ddcea1c480954ba
|
3 |
+
size 988
|
checkpoint-12000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e71950f59e322ffbb0a94be88ee05554b97b740b97bea747e739593db11c43b9
|
3 |
+
size 1000
|
checkpoint-12000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "sd-naruto-model/checkpoint-1500",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-12000/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 10500,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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": 64,
|
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": false,
|
72 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-12500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e85ef425ef5d520711082375460fad326c1fc9d60795690116cb30d551f291f
|
3 |
+
size 14344
|
checkpoint-12500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:971b044be39c256f04af2a12fd12d4dcf9ae5e5d310c0887db9e15dbce71ba9b
|
3 |
+
size 988
|
checkpoint-12500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7467495c6ea967b5801d100432185ae74ac62c2c3534d8f28d164e5eedcbe92d
|
3 |
+
size 1000
|
checkpoint-12500/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "sd-naruto-model/checkpoint-1500",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-12500/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 11000,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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": 64,
|
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": false,
|
72 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-13000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8f1cfbbce69609d6fc623959cd20d5bc0788f46a57aed5976e318c8eb06998a
|
3 |
+
size 14344
|
checkpoint-13000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e77f98967818acefa7b6b48d86d0635b780ab57badf525d74c7b5b70c8009b64
|
3 |
+
size 988
|
checkpoint-13000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee961ed5cbbe8aa04a6a17bc82eac799c17a3005fb0cfac625144c54ed464102
|
3 |
+
size 1000
|
checkpoint-13000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "sd-naruto-model/checkpoint-1500",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-13000/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 11500,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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": 64,
|
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": false,
|
72 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-13500/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91f4add916486a77e9783ab29db13a36a34ee95c67c22fb751e51235b29ac77a
|
3 |
+
size 14344
|
checkpoint-13500/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bb4ee3801b11e2b95773f86abaa2d1e4b1da1e9da1588595ee5a4248d6798c1
|
3 |
+
size 988
|
checkpoint-13500/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd2cb44ffda49b78703f527708e5b05c7884d2efe41a1c8eb6872d68852fa4d1
|
3 |
+
size 1000
|
checkpoint-13500/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "sd-naruto-model/checkpoint-13000",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|
checkpoint-13500/unet_ema/config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"decay": 0.9999,
|
25 |
+
"down_block_types": [
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"CrossAttnDownBlock2D",
|
29 |
+
"DownBlock2D"
|
30 |
+
],
|
31 |
+
"downsample_padding": 1,
|
32 |
+
"dropout": 0.0,
|
33 |
+
"dual_cross_attention": false,
|
34 |
+
"encoder_hid_dim": null,
|
35 |
+
"encoder_hid_dim_type": null,
|
36 |
+
"flip_sin_to_cos": true,
|
37 |
+
"freq_shift": 0,
|
38 |
+
"in_channels": 4,
|
39 |
+
"inv_gamma": 1.0,
|
40 |
+
"layers_per_block": 2,
|
41 |
+
"mid_block_only_cross_attention": null,
|
42 |
+
"mid_block_scale_factor": 1,
|
43 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
44 |
+
"min_decay": 0.0,
|
45 |
+
"norm_eps": 1e-05,
|
46 |
+
"norm_num_groups": 32,
|
47 |
+
"num_attention_heads": null,
|
48 |
+
"num_class_embeds": null,
|
49 |
+
"only_cross_attention": false,
|
50 |
+
"optimization_step": 500,
|
51 |
+
"out_channels": 4,
|
52 |
+
"power": 0.6666666666666666,
|
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": 64,
|
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": false,
|
72 |
+
"update_after_step": 0,
|
73 |
+
"use_ema_warmup": false,
|
74 |
+
"use_linear_projection": false
|
75 |
+
}
|
checkpoint-14000/random_states_0.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7fbfa5d7df68b1fd9bb734ecba668973b5677a864eb9c3b78338bc7487b4abcd
|
3 |
+
size 14344
|
checkpoint-14000/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8972e137dff582ed156c48a434d8d5304443a88bca38ef8e7f0e80298e6f0533
|
3 |
+
size 988
|
checkpoint-14000/scheduler.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee032204bba8930df676bada22732e1d1d4fce2e74de1dd6725c0a0c5840cb19
|
3 |
+
size 1000
|
checkpoint-14000/unet/config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.30.0.dev0",
|
4 |
+
"_name_or_path": "sd-naruto-model/checkpoint-13000",
|
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": 8,
|
10 |
+
"attention_type": "default",
|
11 |
+
"block_out_channels": [
|
12 |
+
320,
|
13 |
+
640,
|
14 |
+
1280,
|
15 |
+
1280
|
16 |
+
],
|
17 |
+
"center_input_sample": false,
|
18 |
+
"class_embed_type": null,
|
19 |
+
"class_embeddings_concat": false,
|
20 |
+
"conv_in_kernel": 3,
|
21 |
+
"conv_out_kernel": 3,
|
22 |
+
"cross_attention_dim": 768,
|
23 |
+
"cross_attention_norm": null,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dropout": 0.0,
|
32 |
+
"dual_cross_attention": false,
|
33 |
+
"encoder_hid_dim": null,
|
34 |
+
"encoder_hid_dim_type": null,
|
35 |
+
"flip_sin_to_cos": true,
|
36 |
+
"freq_shift": 0,
|
37 |
+
"in_channels": 4,
|
38 |
+
"layers_per_block": 2,
|
39 |
+
"mid_block_only_cross_attention": null,
|
40 |
+
"mid_block_scale_factor": 1,
|
41 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
42 |
+
"norm_eps": 1e-05,
|
43 |
+
"norm_num_groups": 32,
|
44 |
+
"num_attention_heads": null,
|
45 |
+
"num_class_embeds": null,
|
46 |
+
"only_cross_attention": false,
|
47 |
+
"out_channels": 4,
|
48 |
+
"projection_class_embeddings_input_dim": null,
|
49 |
+
"resnet_out_scale_factor": 1.0,
|
50 |
+
"resnet_skip_time_act": false,
|
51 |
+
"resnet_time_scale_shift": "default",
|
52 |
+
"reverse_transformer_layers_per_block": null,
|
53 |
+
"sample_size": 64,
|
54 |
+
"time_cond_proj_dim": null,
|
55 |
+
"time_embedding_act_fn": null,
|
56 |
+
"time_embedding_dim": null,
|
57 |
+
"time_embedding_type": "positional",
|
58 |
+
"timestep_post_act": null,
|
59 |
+
"transformer_layers_per_block": 1,
|
60 |
+
"up_block_types": [
|
61 |
+
"UpBlock2D",
|
62 |
+
"CrossAttnUpBlock2D",
|
63 |
+
"CrossAttnUpBlock2D",
|
64 |
+
"CrossAttnUpBlock2D"
|
65 |
+
],
|
66 |
+
"upcast_attention": false,
|
67 |
+
"use_linear_projection": false
|
68 |
+
}
|