Instructions to use Miayan/project with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Miayan/project with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Miayan/project", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
Add checkpoint for train_ex6_3
Browse files- train_ex6_3/checkpoint-55000/controlnet/config.json +56 -0
- train_ex6_3/checkpoint-55000/controlnet/diffusion_pytorch_model.safetensors +3 -0
- train_ex6_3/checkpoint-55000/custom_encoder/config.json +8 -0
- train_ex6_3/checkpoint-55000/custom_encoder/diffusion_pytorch_model.safetensors +3 -0
- train_ex6_3/checkpoint-55000/custom_unet.pth +3 -0
- train_ex6_3/checkpoint-55000/custom_unet/config.json +73 -0
- train_ex6_3/checkpoint-55000/custom_unet/diffusion_pytorch_model.bin +3 -0
- train_ex6_3/checkpoint-55000/optimizer.bin +3 -0
- train_ex6_3/checkpoint-55000/random_states_0.pkl +3 -0
- train_ex6_3/checkpoint-55000/scheduler.bin +3 -0
- train_ex6_3/config.json +56 -0
- train_ex6_3/diffusion_pytorch_model.safetensors +3 -0
train_ex6_3/checkpoint-55000/controlnet/config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.33.1",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"addition_embed_type": null,
|
| 6 |
+
"addition_embed_type_num_heads": 64,
|
| 7 |
+
"addition_time_embed_dim": null,
|
| 8 |
+
"attention_head_dim": [
|
| 9 |
+
5,
|
| 10 |
+
10,
|
| 11 |
+
20,
|
| 12 |
+
20
|
| 13 |
+
],
|
| 14 |
+
"block_out_channels": [
|
| 15 |
+
320,
|
| 16 |
+
640,
|
| 17 |
+
1280,
|
| 18 |
+
1280
|
| 19 |
+
],
|
| 20 |
+
"class_embed_type": null,
|
| 21 |
+
"conditioning_channels": 6,
|
| 22 |
+
"conditioning_embedding_out_channels": [
|
| 23 |
+
16,
|
| 24 |
+
32,
|
| 25 |
+
96,
|
| 26 |
+
256
|
| 27 |
+
],
|
| 28 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 29 |
+
"cross_attention_dim": 1024,
|
| 30 |
+
"down_block_types": [
|
| 31 |
+
"CrossAttnDownBlock2D",
|
| 32 |
+
"CrossAttnDownBlock2D",
|
| 33 |
+
"CrossAttnDownBlock2D",
|
| 34 |
+
"DownBlock2D"
|
| 35 |
+
],
|
| 36 |
+
"downsample_padding": 1,
|
| 37 |
+
"encoder_hid_dim": null,
|
| 38 |
+
"encoder_hid_dim_type": null,
|
| 39 |
+
"flip_sin_to_cos": true,
|
| 40 |
+
"freq_shift": 0,
|
| 41 |
+
"global_pool_conditions": false,
|
| 42 |
+
"in_channels": 4,
|
| 43 |
+
"layers_per_block": 2,
|
| 44 |
+
"mid_block_scale_factor": 1,
|
| 45 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 46 |
+
"norm_eps": 1e-05,
|
| 47 |
+
"norm_num_groups": 32,
|
| 48 |
+
"num_attention_heads": null,
|
| 49 |
+
"num_class_embeds": null,
|
| 50 |
+
"only_cross_attention": false,
|
| 51 |
+
"projection_class_embeddings_input_dim": null,
|
| 52 |
+
"resnet_time_scale_shift": "default",
|
| 53 |
+
"transformer_layers_per_block": 1,
|
| 54 |
+
"upcast_attention": true,
|
| 55 |
+
"use_linear_projection": true
|
| 56 |
+
}
|
train_ex6_3/checkpoint-55000/controlnet/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2edafa3735b6cf5c4a12e55d7297e480076b7ccee42c5ae3bbd716b2a222af0c
|
| 3 |
+
size 1461729992
|
train_ex6_3/checkpoint-55000/custom_encoder/config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"Bc": 4,
|
| 3 |
+
"Bi": 0,
|
| 4 |
+
"K": 4,
|
| 5 |
+
"_class_name": "CustomEncoder",
|
| 6 |
+
"_diffusers_version": "0.33.1",
|
| 7 |
+
"cross_dim": 1024
|
| 8 |
+
}
|
train_ex6_3/checkpoint-55000/custom_encoder/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cf01b0d53a04b29266922ce2d732e60ce4aea149178d4163883bba42f019e95
|
| 3 |
+
size 4523608
|
train_ex6_3/checkpoint-55000/custom_unet.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7ebfd049e4628604ca59d003b67fbfaf9a30b8d92cd3ddfa6f3c2e2f4f273d5
|
| 3 |
+
size 3463973299
|
train_ex6_3/checkpoint-55000/custom_unet/config.json
ADDED
|
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "UNet2DConditionModel",
|
| 3 |
+
"_diffusers_version": "0.33.1",
|
| 4 |
+
"_name_or_path": "/mnt/HDD3/miayan/paper/envs/huggingface_cache/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6",
|
| 5 |
+
"act_fn": "silu",
|
| 6 |
+
"addition_embed_type": null,
|
| 7 |
+
"addition_embed_type_num_heads": 64,
|
| 8 |
+
"addition_time_embed_dim": null,
|
| 9 |
+
"attention_head_dim": [
|
| 10 |
+
5,
|
| 11 |
+
10,
|
| 12 |
+
20,
|
| 13 |
+
20
|
| 14 |
+
],
|
| 15 |
+
"attention_type": "default",
|
| 16 |
+
"block_out_channels": [
|
| 17 |
+
320,
|
| 18 |
+
640,
|
| 19 |
+
1280,
|
| 20 |
+
1280
|
| 21 |
+
],
|
| 22 |
+
"center_input_sample": false,
|
| 23 |
+
"class_embed_type": null,
|
| 24 |
+
"class_embeddings_concat": false,
|
| 25 |
+
"conv_in_kernel": 3,
|
| 26 |
+
"conv_out_kernel": 3,
|
| 27 |
+
"cross_attention_dim": 1024,
|
| 28 |
+
"cross_attention_norm": null,
|
| 29 |
+
"down_block_types": [
|
| 30 |
+
"CrossAttnDownBlock2D",
|
| 31 |
+
"CrossAttnDownBlock2D",
|
| 32 |
+
"CrossAttnDownBlock2D",
|
| 33 |
+
"DownBlock2D"
|
| 34 |
+
],
|
| 35 |
+
"downsample_padding": 1,
|
| 36 |
+
"dropout": 0.0,
|
| 37 |
+
"dual_cross_attention": false,
|
| 38 |
+
"encoder_hid_dim": null,
|
| 39 |
+
"encoder_hid_dim_type": null,
|
| 40 |
+
"flip_sin_to_cos": true,
|
| 41 |
+
"freq_shift": 0,
|
| 42 |
+
"in_channels": 8,
|
| 43 |
+
"layers_per_block": 2,
|
| 44 |
+
"mid_block_only_cross_attention": null,
|
| 45 |
+
"mid_block_scale_factor": 1,
|
| 46 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 47 |
+
"norm_eps": 1e-05,
|
| 48 |
+
"norm_num_groups": 32,
|
| 49 |
+
"num_attention_heads": null,
|
| 50 |
+
"num_class_embeds": null,
|
| 51 |
+
"only_cross_attention": false,
|
| 52 |
+
"out_channels": 4,
|
| 53 |
+
"projection_class_embeddings_input_dim": null,
|
| 54 |
+
"resnet_out_scale_factor": 1.0,
|
| 55 |
+
"resnet_skip_time_act": false,
|
| 56 |
+
"resnet_time_scale_shift": "default",
|
| 57 |
+
"reverse_transformer_layers_per_block": null,
|
| 58 |
+
"sample_size": 96,
|
| 59 |
+
"time_cond_proj_dim": null,
|
| 60 |
+
"time_embedding_act_fn": null,
|
| 61 |
+
"time_embedding_dim": null,
|
| 62 |
+
"time_embedding_type": "positional",
|
| 63 |
+
"timestep_post_act": null,
|
| 64 |
+
"transformer_layers_per_block": 1,
|
| 65 |
+
"up_block_types": [
|
| 66 |
+
"UpBlock2D",
|
| 67 |
+
"CrossAttnUpBlock2D",
|
| 68 |
+
"CrossAttnUpBlock2D",
|
| 69 |
+
"CrossAttnUpBlock2D"
|
| 70 |
+
],
|
| 71 |
+
"upcast_attention": true,
|
| 72 |
+
"use_linear_projection": true
|
| 73 |
+
}
|
train_ex6_3/checkpoint-55000/custom_unet/diffusion_pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d81ce7dcdaf1fc938d21aec272384eca69a7a6dfa9a5949228c35d07ac1c00e4
|
| 3 |
+
size 3463934051
|
train_ex6_3/checkpoint-55000/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f7a08e7bef2bb1e083aea9699088541c50a23de3d7b3be0b03eee09f397a0d7
|
| 3 |
+
size 5573543069
|
train_ex6_3/checkpoint-55000/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed4d7868df025db64dc760ee0950a93f61f470ba476c08ff2ff1604ab8de2f58
|
| 3 |
+
size 14885
|
train_ex6_3/checkpoint-55000/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78a69301bd8f68990bda5d5d7e9764492196ab672d9c24ec00350a30fa59a9aa
|
| 3 |
+
size 1401
|
train_ex6_3/config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "ControlNetModel",
|
| 3 |
+
"_diffusers_version": "0.33.1",
|
| 4 |
+
"act_fn": "silu",
|
| 5 |
+
"addition_embed_type": null,
|
| 6 |
+
"addition_embed_type_num_heads": 64,
|
| 7 |
+
"addition_time_embed_dim": null,
|
| 8 |
+
"attention_head_dim": [
|
| 9 |
+
5,
|
| 10 |
+
10,
|
| 11 |
+
20,
|
| 12 |
+
20
|
| 13 |
+
],
|
| 14 |
+
"block_out_channels": [
|
| 15 |
+
320,
|
| 16 |
+
640,
|
| 17 |
+
1280,
|
| 18 |
+
1280
|
| 19 |
+
],
|
| 20 |
+
"class_embed_type": null,
|
| 21 |
+
"conditioning_channels": 6,
|
| 22 |
+
"conditioning_embedding_out_channels": [
|
| 23 |
+
16,
|
| 24 |
+
32,
|
| 25 |
+
96,
|
| 26 |
+
256
|
| 27 |
+
],
|
| 28 |
+
"controlnet_conditioning_channel_order": "rgb",
|
| 29 |
+
"cross_attention_dim": 1024,
|
| 30 |
+
"down_block_types": [
|
| 31 |
+
"CrossAttnDownBlock2D",
|
| 32 |
+
"CrossAttnDownBlock2D",
|
| 33 |
+
"CrossAttnDownBlock2D",
|
| 34 |
+
"DownBlock2D"
|
| 35 |
+
],
|
| 36 |
+
"downsample_padding": 1,
|
| 37 |
+
"encoder_hid_dim": null,
|
| 38 |
+
"encoder_hid_dim_type": null,
|
| 39 |
+
"flip_sin_to_cos": true,
|
| 40 |
+
"freq_shift": 0,
|
| 41 |
+
"global_pool_conditions": false,
|
| 42 |
+
"in_channels": 4,
|
| 43 |
+
"layers_per_block": 2,
|
| 44 |
+
"mid_block_scale_factor": 1,
|
| 45 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
| 46 |
+
"norm_eps": 1e-05,
|
| 47 |
+
"norm_num_groups": 32,
|
| 48 |
+
"num_attention_heads": null,
|
| 49 |
+
"num_class_embeds": null,
|
| 50 |
+
"only_cross_attention": false,
|
| 51 |
+
"projection_class_embeddings_input_dim": null,
|
| 52 |
+
"resnet_time_scale_shift": "default",
|
| 53 |
+
"transformer_layers_per_block": 1,
|
| 54 |
+
"upcast_attention": true,
|
| 55 |
+
"use_linear_projection": true
|
| 56 |
+
}
|
train_ex6_3/diffusion_pytorch_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94193bf4dbabbea2cff4ec7e911239708fdfa17a47897249c1941b0462019f20
|
| 3 |
+
size 1461729992
|