Commit
•
b3e38d4
1
Parent(s):
20ee17e
End of training
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- 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/unet/config.json +68 -0
- checkpoint-1000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-1000/unet_ema/config.json +75 -0
- checkpoint-1000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-10000/optimizer.bin +3 -0
- checkpoint-10000/random_states_0.pkl +3 -0
- checkpoint-10000/scheduler.bin +3 -0
- checkpoint-10000/unet/config.json +68 -0
- checkpoint-10000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-10000/unet_ema/config.json +75 -0
- checkpoint-10000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-10500/optimizer.bin +3 -0
- checkpoint-10500/random_states_0.pkl +3 -0
- checkpoint-10500/scheduler.bin +3 -0
- checkpoint-10500/unet/config.json +68 -0
- checkpoint-10500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-10500/unet_ema/config.json +75 -0
- checkpoint-10500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-11000/optimizer.bin +3 -0
- checkpoint-11000/random_states_0.pkl +3 -0
- checkpoint-11000/scheduler.bin +3 -0
- checkpoint-11000/unet/config.json +68 -0
- checkpoint-11000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-11000/unet_ema/config.json +75 -0
- checkpoint-11000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-11500/optimizer.bin +3 -0
- checkpoint-11500/random_states_0.pkl +3 -0
- checkpoint-11500/scheduler.bin +3 -0
- checkpoint-11500/unet/config.json +68 -0
- checkpoint-11500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-11500/unet_ema/config.json +75 -0
- checkpoint-11500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-12000/optimizer.bin +3 -0
- checkpoint-12000/random_states_0.pkl +3 -0
- checkpoint-12000/scheduler.bin +3 -0
- checkpoint-12000/unet/config.json +68 -0
- checkpoint-12000/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-12000/unet_ema/config.json +75 -0
- checkpoint-12000/unet_ema/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-12500/optimizer.bin +3 -0
- checkpoint-12500/random_states_0.pkl +3 -0
- checkpoint-12500/scheduler.bin +3 -0
- checkpoint-12500/unet/config.json +68 -0
- checkpoint-12500/unet/diffusion_pytorch_model.safetensors +3 -0
- checkpoint-12500/unet_ema/config.json +75 -0
- checkpoint-12500/unet_ema/diffusion_pytorch_model.safetensors +3 -0
README.md
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
license: creativeml-openrail-m
|
| 4 |
+
base_model: runwayml/stable-diffusion-v1-5
|
| 5 |
+
datasets:
|
| 6 |
+
- None
|
| 7 |
+
tags:
|
| 8 |
+
- stable-diffusion
|
| 9 |
+
- stable-diffusion-diffusers
|
| 10 |
+
- text-to-image
|
| 11 |
+
- diffusers
|
| 12 |
+
inference: true
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# Text-to-image finetuning - juliajoanna/sd-runwayml-flintstones-model
|
| 16 |
+
|
| 17 |
+
This pipeline was finetuned from **runwayml/stable-diffusion-v1-5** on the **None** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Fred is driving a car']:
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
## Pipeline usage
|
| 23 |
+
|
| 24 |
+
You can use the pipeline like so:
|
| 25 |
+
|
| 26 |
+
```python
|
| 27 |
+
from diffusers import DiffusionPipeline
|
| 28 |
+
import torch
|
| 29 |
+
|
| 30 |
+
pipeline = DiffusionPipeline.from_pretrained("juliajoanna/sd-runwayml-flintstones-model", torch_dtype=torch.float16)
|
| 31 |
+
prompt = "Fred is driving a car"
|
| 32 |
+
image = pipeline(prompt).images[0]
|
| 33 |
+
image.save("my_image.png")
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
+
## Training info
|
| 37 |
+
|
| 38 |
+
These are the key hyperparameters used during training:
|
| 39 |
+
|
| 40 |
+
* Epochs: 0
|
| 41 |
+
* Learning rate: 1e-05
|
| 42 |
+
* Batch size: 1
|
| 43 |
+
* Gradient accumulation steps: 4
|
| 44 |
+
* Image resolution: 512
|
| 45 |
+
* Mixed-precision: None
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/dream0team/text2image-fine-tune/runs/h76tuji9).
|
checkpoint-1000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bed9d1d4bf9d1ee3a6de3f05dc9080162c273961ccfd76c6fb5c4ab79e03f62
|
| 3 |
+
size 6876750164
|
checkpoint-1000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7f769f0779eb13ba4a2ff2318675a9878d554b3932621a47caae59830e9b752
|
| 3 |
+
size 14344
|
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": "0.22.0.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/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0a27d5cd0c5b803453991c489427ab6d7cb498c795709c0e686a06540b85f5e
|
| 3 |
+
size 3438167536
|
checkpoint-1000/unet_ema/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.22.0.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-1000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fab18f9ce674fab936eef12f03f8862adcbb7e0a27be5ef6eeac92d0ce7489c2
|
| 3 |
+
size 3438167536
|
checkpoint-10000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ac3182b086312bd9879f0233ca11723f43e1872ad39eccb23cd35ef5790c3b5
|
| 3 |
+
size 6876750164
|
checkpoint-10000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22949c57a3c9a05901e71fdd0c175368565d106d39f9c626e0fbe9035d9a25b7
|
| 3 |
+
size 14344
|
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": "0.22.0.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-10000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08e8c1b1259d997fda199899e11e033145e8906fe02fa4de44db65c68023c279
|
| 3 |
+
size 3438167536
|
checkpoint-10000/unet_ema/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.22.0.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-10000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f054d4dbb524c260ffbfa3340e883ace18c7647355f017310c2fbc4bbe6cff8b
|
| 3 |
+
size 3438167536
|
checkpoint-10500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:005323d10e3fe1bfaf0b724a547f2d8f6946e13a19df76ba2cf209645e54ef84
|
| 3 |
+
size 6876750164
|
checkpoint-10500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99a446791ae14995266a44c1b51f14a4635afbfd764cf51a5f31fb40adc6c8b8
|
| 3 |
+
size 14344
|
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": "0.22.0.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-10500/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a9a1b5ce6a4659b0803671d9447986d15667f024e7e23591eb7a690a6793e98
|
| 3 |
+
size 3438167536
|
checkpoint-10500/unet_ema/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.22.0.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-10500/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6eb958ba163330fd479a4ea24044a43d8bc931b2e1da48fa5084240f335ed4a4
|
| 3 |
+
size 3438167536
|
checkpoint-11000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7611fb4dde792e8963566ab1dc884762194a3e790e35a90fe39c80734845cd5f
|
| 3 |
+
size 6876750164
|
checkpoint-11000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:381790fe651a11f73339a9904975ce7f449d0883f481f21c625f20d57a82f2d0
|
| 3 |
+
size 14344
|
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": "0.22.0.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-11000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86636d1142816eeb8e8366ac062600ef233cace2660f0b5a783ee7f2037983c0
|
| 3 |
+
size 3438167536
|
checkpoint-11000/unet_ema/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.22.0.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-11000/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:964ad5e71efff24fb8496002d8d5912027ce4489920d3a84c86e1ce5c65fa90f
|
| 3 |
+
size 3438167536
|
checkpoint-11500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b882a22c9793b088914417b92075e3f8836735fe66c8fc573bb8012a83bf7d1
|
| 3 |
+
size 6876750164
|
checkpoint-11500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac7ace65714eff8997fb2eab4be4762d3a345de9ca3ff1e5f7fe03896f39218a
|
| 3 |
+
size 14344
|
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": "0.22.0.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-11500/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f851482471e11ff9e18a65cd12d28b3eb77b70e776170745e9c80bd964dbe9fb
|
| 3 |
+
size 3438167536
|
checkpoint-11500/unet_ema/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.22.0.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-11500/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8172527661debc0f66655b325ff5bc5d8a37deb31984870e9595c83b3f2f251a
|
| 3 |
+
size 3438167536
|
checkpoint-12000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6150bb890f07ff8d868d292dfab6091f25b722ed8e592023092a817a6c534382
|
| 3 |
+
size 6876750164
|
checkpoint-12000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ed0c98dfa81e953853968701a8ecbe72e16392cec5a0e8e1465baeeee354b89
|
| 3 |
+
size 14344
|
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": "0.22.0.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-12000/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:161ab70093091f10ac9eca9b3f996d7a4b0fd0532c28dda53dbf8521349007d2
|
| 3 |
+
size 3438167536
|
checkpoint-12000/unet_ema/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.22.0.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": 12000,
|
| 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/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c154f17efda3cb15148ab2d86c97b26f0eafe76603cea6c96270ec31aa56473b
|
| 3 |
+
size 3438167536
|
checkpoint-12500/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af3c98badd8aff113caf56afcc10cf2b0ddcd2ac0dcf8c7b9e702e56ef813e63
|
| 3 |
+
size 6876750164
|
checkpoint-12500/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14565520036cf2f572e417f12d6aac73728da2ba14c8f6afecb2a1218e097969
|
| 3 |
+
size 14344
|
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": "0.22.0.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-12500/unet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:083b03612cec9b68d94a4e36acf2047b2b2eef86c465e3e52464aada8f282158
|
| 3 |
+
size 3438167536
|
checkpoint-12500/unet_ema/config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.22.0.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": 12500,
|
| 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/unet_ema/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d1e11e19b85cd538035fc9e70016acd7677a74432b6fc645a3e749f5354ca4e
|
| 3 |
+
size 3438167536
|