End of training
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +4 -0
- README.md +48 -0
- checkpoint-1000/optimizer.bin +3 -0
- checkpoint-1000/random_states_0.pkl +3 -0
- checkpoint-1000/scheduler.bin +3 -0
- checkpoint-1000/text_encoder/config.json +25 -0
- checkpoint-1000/text_encoder/model.safetensors +3 -0
- checkpoint-1000/unet/config.json +68 -0
- checkpoint-1000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-1500/optimizer.bin +3 -0
- checkpoint-1500/random_states_0.pkl +3 -0
- checkpoint-1500/scheduler.bin +3 -0
- checkpoint-1500/text_encoder/config.json +25 -0
- checkpoint-1500/text_encoder/model.safetensors +3 -0
- checkpoint-1500/unet/config.json +68 -0
- checkpoint-1500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2000/optimizer.bin +3 -0
- checkpoint-2000/random_states_0.pkl +3 -0
- checkpoint-2000/scheduler.bin +3 -0
- checkpoint-2000/text_encoder/config.json +25 -0
- checkpoint-2000/text_encoder/model.safetensors +3 -0
- checkpoint-2000/unet/config.json +68 -0
- checkpoint-2000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-2500/optimizer.bin +3 -0
- checkpoint-2500/random_states_0.pkl +3 -0
- checkpoint-2500/scheduler.bin +3 -0
- checkpoint-2500/text_encoder/config.json +25 -0
- checkpoint-2500/text_encoder/model.safetensors +3 -0
- checkpoint-2500/unet/config.json +68 -0
- checkpoint-2500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3000/optimizer.bin +3 -0
- checkpoint-3000/random_states_0.pkl +3 -0
- checkpoint-3000/scheduler.bin +3 -0
- checkpoint-3000/text_encoder/config.json +25 -0
- checkpoint-3000/text_encoder/model.safetensors +3 -0
- checkpoint-3000/unet/config.json +68 -0
- checkpoint-3000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-3500/optimizer.bin +3 -0
- checkpoint-3500/random_states_0.pkl +3 -0
- checkpoint-3500/scheduler.bin +3 -0
- checkpoint-3500/text_encoder/config.json +25 -0
- checkpoint-3500/text_encoder/model.safetensors +3 -0
- checkpoint-3500/unet/config.json +68 -0
- checkpoint-3500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-4000/optimizer.bin +3 -0
- checkpoint-4000/random_states_0.pkl +3 -0
- checkpoint-4000/scheduler.bin +3 -0
- checkpoint-4000/text_encoder/config.json +25 -0
- checkpoint-4000/text_encoder/model.safetensors +3 -0
- checkpoint-4000/unet/config.json +68 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
image_0.png filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
image_1.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
image_2.png filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
image_3.png filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
|
| 3 |
+
library_name: diffusers
|
| 4 |
+
license: creativeml-openrail-m
|
| 5 |
+
inference: true
|
| 6 |
+
instance_prompt: A photo of a leaf infected with late blight disease. The leaf has
|
| 7 |
+
blackish brown regions of infection, hd, 4k
|
| 8 |
+
tags:
|
| 9 |
+
- text-to-image
|
| 10 |
+
- dreambooth
|
| 11 |
+
- diffusers-training
|
| 12 |
+
- stable-diffusion
|
| 13 |
+
- stable-diffusion-diffusers
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the training script had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
# DreamBooth - ButterChicken98/pv_lb_v3
|
| 21 |
+
|
| 22 |
+
This is a dreambooth model derived from stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were trained on A photo of a leaf infected with late blight disease. The leaf has blackish brown regions of infection, hd, 4k using [DreamBooth](https://dreambooth.github.io/).
|
| 23 |
+
You can find some example images in the following.
|
| 24 |
+
|
| 25 |
+

|
| 26 |
+

|
| 27 |
+

|
| 28 |
+

|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
DreamBooth for the text encoder was enabled: True.
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
## Intended uses & limitations
|
| 35 |
+
|
| 36 |
+
#### How to use
|
| 37 |
+
|
| 38 |
+
```python
|
| 39 |
+
# TODO: add an example code snippet for running this diffusion pipeline
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
#### Limitations and bias
|
| 43 |
+
|
| 44 |
+
[TODO: provide examples of latent issues and potential remediations]
|
| 45 |
+
|
| 46 |
+
## Training details
|
| 47 |
+
|
| 48 |
+
[TODO: describe the data used to train the model]
|
checkpoint-1000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:031af8f9ab193106bfd3e6b27c5b1125d77912ea84aa1e63b474fb1255953130
|
| 3 |
+
size 7861403640
|
checkpoint-1000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5fc55159c113198cde79cd0b41325b186a456efb8cb017a8dae672c8c878077
|
| 3 |
+
size 14668
|
checkpoint-1000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b49a3223b5c20fde8b25837354f33e3194e0751f1444517ba10e67d7f345cf0a
|
| 3 |
+
size 1000
|
checkpoint-1000/text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 768,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.49.0",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
checkpoint-1000/text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48c305ffdd48d88c2d82fc3197e206de7708fcc0ec3c8b619a5a5b27653554e2
|
| 3 |
+
size 492265168
|
checkpoint-1000/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-5/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/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6746aeacd87ec9cd540a73e71820825976a9937fd22103b1e52e3f0b2166a48
|
| 3 |
+
size 3438167536
|
checkpoint-1500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99fa9c5134969efc2fe8658ff29ba2b76263dec0098b43d46ce03ec845171ba7
|
| 3 |
+
size 7861403640
|
checkpoint-1500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34b23cbdad8e9f8b4002cef93473191e6ac024f23a4e6e0d69c6d1803277e472
|
| 3 |
+
size 14668
|
checkpoint-1500/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acc37d0068ef55831d917f8deb3050db935c8f9e20483262b9c4d3e0bc22baab
|
| 3 |
+
size 1000
|
checkpoint-1500/text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 768,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.49.0",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
checkpoint-1500/text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b5fb02a92afc74fcabd8f82108831ed58ce185b5e92da9fc32806004e06ffa9
|
| 3 |
+
size 492265168
|
checkpoint-1500/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-5/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-1500/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8f0d5f4b77625e7838dd4af8a06f130ea3f9d65e8d89b0527b84c2ef71ba3df
|
| 3 |
+
size 3438167536
|
checkpoint-2000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed3e9df07a3b71a984ac2d39e000da7c2b2820fad41b927d0bb0ece4a9f471fa
|
| 3 |
+
size 7861403640
|
checkpoint-2000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e4a12cd2ada417ad7dfa448dbb92af39237fee07426f64e7eda8ebab7fd559a
|
| 3 |
+
size 14668
|
checkpoint-2000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:123b6cc6b2b24c64d375d5b6f6c7fce10fff0fb6b2d2142d241b7bc9b76e1018
|
| 3 |
+
size 1000
|
checkpoint-2000/text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 768,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.49.0",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
checkpoint-2000/text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfcd93e22f169bcf945192739b7fc203c700aa1b57c41f37a03e096639b9443e
|
| 3 |
+
size 492265168
|
checkpoint-2000/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-5/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-2000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03367ec77d6f6bbb563190b7d972950567531732c81349ff5fd6eaa41c997ec3
|
| 3 |
+
size 3438167536
|
checkpoint-2500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:396cb2e220245976a0c469d07b11d80e64e007e41aa53b594507f67937139425
|
| 3 |
+
size 7861403640
|
checkpoint-2500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d97cb63e260bc00e70ffae39551a35bfce026fd535b2377bcccf64ceb84d986
|
| 3 |
+
size 14668
|
checkpoint-2500/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa2dd6d5da641bd88688ca47ad26c53eaafc9aec172958ac6c976b7ec0d0d2fc
|
| 3 |
+
size 1000
|
checkpoint-2500/text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 768,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.49.0",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
checkpoint-2500/text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37313d5c2e7de1300bed53f4ebd26642b8f6f6c6ec604bd60c4def6bab0081d4
|
| 3 |
+
size 492265168
|
checkpoint-2500/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-5/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-2500/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0603fea4d34a93b753aacba83d0726d0cddd8bd0eb06312a3793b48158b13e7
|
| 3 |
+
size 3438167536
|
checkpoint-3000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91368ef678b6d381afba596825e421ca71ee2eb4406d1d63dcbf56f0946950d0
|
| 3 |
+
size 7861403640
|
checkpoint-3000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bf74369c4fbc9addcc674706b1fb4d67107b0d14340ca0ae2822b9dcb248fc4
|
| 3 |
+
size 14668
|
checkpoint-3000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c322645f4f53661bd80098cd26e239947db4cd7e988082dbb50ed06e380c11bb
|
| 3 |
+
size 1000
|
checkpoint-3000/text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 768,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.49.0",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
checkpoint-3000/text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4b31c3343c2042dc092c7b779881800c8c6499526be7a743a22aa5a60262c0e
|
| 3 |
+
size 492265168
|
checkpoint-3000/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-5/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-3000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7831af09637f9286d5fc9c1cbffa17bffba6c8e76528345cd137f6c4bae6c398
|
| 3 |
+
size 3438167536
|
checkpoint-3500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e63b73dbb1d802cc593b461cdd600dbddd8f21ec6c3847a3bdc4a8e9fbb9a42
|
| 3 |
+
size 7861403640
|
checkpoint-3500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aab98eda0d4b795d5ec1a2e15c24d6bf1a28ada9d8cd43ad9349f791d73873d4
|
| 3 |
+
size 14668
|
checkpoint-3500/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1f4e88742e2b1eb00d263f126e185dcd14bf920478997f7d3567176ff3a2b32
|
| 3 |
+
size 1000
|
checkpoint-3500/text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 768,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.49.0",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
checkpoint-3500/text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3154cdd175ae41f1157c7c5bc87aea959fff266ef8a1ff95828c473b2a69726
|
| 3 |
+
size 492265168
|
checkpoint-3500/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-5/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-3500/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e947466becea446536b7702fd72efa11649f3945b9b0212b8b539ae82db3352c
|
| 3 |
+
size 3438167536
|
checkpoint-4000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9914cb662250f90712067d0ffad30a6127370cbe10478a39a3618cfd90a3f6d
|
| 3 |
+
size 7861403640
|
checkpoint-4000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:972cfaef58e7bb9b77cf088879099a9f965b9eccfa582bec41a8f2c79f80e249
|
| 3 |
+
size 14668
|
checkpoint-4000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a60aaa9dc4ef51ca8a804b2e7b27541e45df6748e9713cfb398e294a11d84227
|
| 3 |
+
size 1000
|
checkpoint-4000/text_encoder/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "stable-diffusion-v1-5/stable-diffusion-v1-5",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPTextModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"dropout": 0.0,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "quick_gelu",
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_factor": 1.0,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 77,
|
| 17 |
+
"model_type": "clip_text_model",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"projection_dim": 768,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.49.0",
|
| 24 |
+
"vocab_size": 49408
|
| 25 |
+
}
|
checkpoint-4000/text_encoder/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06d23214117661348fec558e09efcc09318294cfe3832190e51a7506e8d5ec2e
|
| 3 |
+
size 492265168
|
checkpoint-4000/unet/config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"_name_or_path": "stable-diffusion-v1-5/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 |
+
}
|