ViscoseBean
commited on
Commit
•
90a1984
1
Parent(s):
1129ad3
Upload 4 files
Browse files- README.md +45 -1
- config.json +45 -0
- control_v1p_sd15_brightness.safetensors +3 -0
- control_v1p_sd15_brightness.yaml +79 -0
README.md
CHANGED
@@ -1,3 +1,47 @@
|
|
1 |
---
|
2 |
-
license:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
license: creativeml-openrail-m
|
3 |
+
datasets:
|
4 |
+
- ioclab/grayscale_image_aesthetic_3M
|
5 |
+
language:
|
6 |
+
- en
|
7 |
+
library_name: diffusers
|
8 |
+
tags:
|
9 |
+
- image-to-image
|
10 |
+
- controlnet
|
11 |
---
|
12 |
+
|
13 |
+
# Model Card for ioclab/ioc-controlnet
|
14 |
+
|
15 |
+
This model brings brightness control to Stable Diffusion, allowing users to colorize grayscale images or recolor generated images.
|
16 |
+
|
17 |
+
## Model Details
|
18 |
+
|
19 |
+
- **Developed by:** [@ciaochaos](https://github.com/ciaochaos)
|
20 |
+
- **Shared by [optional]:** [More Information Needed]
|
21 |
+
- **Model type:** Stable Diffusion ControlNet model for [web UI](https://github.com/AUTOMATIC1111/stable-diffusion-webui)
|
22 |
+
- **License:** [The CreativeML OpenRAIL M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license) is an [Open RAIL M license](https://www.licenses.ai/blog/2022/8/18/naming-convention-of-responsible-ai-licenses), adapted from the work that [BigScience](https://bigscience.huggingface.co/) and [the RAIL Initiative](https://www.licenses.ai/) are jointly carrying in the area of responsible AI licensing. See also [the article about the BLOOM Open RAIL license](https://bigscience.huggingface.co/blog/the-bigscience-rail-license) on which our license is based.
|
23 |
+
|
24 |
+
|
25 |
+
## Uses
|
26 |
+
|
27 |
+
|
28 |
+
### HuggingFace Space Demo
|
29 |
+
|
30 |
+
[huggingface.co/spaces/ioclab/brightness-controlnet](https://huggingface.co/spaces/ioclab/brightness-controlnet)
|
31 |
+
|
32 |
+
### Direct Use
|
33 |
+
|
34 |
+
[More Information Needed]
|
35 |
+
|
36 |
+
### Out-of-Scope Use
|
37 |
+
|
38 |
+
[More Information Needed]
|
39 |
+
|
40 |
+
## Bias, Risks, and Limitations
|
41 |
+
|
42 |
+
[More Information Needed]
|
43 |
+
|
44 |
+
|
45 |
+
## More Info
|
46 |
+
|
47 |
+
[Brightness ControlNet 训练流程](https://aigc.ioclab.com/sd-showcase/brightness-controlnet.html) (Chinese)
|
config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "ControlNetModel",
|
3 |
+
"_diffusers_version": "0.16.0.dev0",
|
4 |
+
"_name_or_path": "./controlnet_flax",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"class_embed_type": null,
|
14 |
+
"conditioning_embedding_out_channels": [
|
15 |
+
16,
|
16 |
+
32,
|
17 |
+
96,
|
18 |
+
256
|
19 |
+
],
|
20 |
+
"controlnet_conditioning_channel_order": "rgb",
|
21 |
+
"cross_attention_dim": 768,
|
22 |
+
"down_block_types": [
|
23 |
+
"CrossAttnDownBlock2D",
|
24 |
+
"CrossAttnDownBlock2D",
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"DownBlock2D"
|
27 |
+
],
|
28 |
+
"downsample_padding": 1,
|
29 |
+
"dropout": 0.0,
|
30 |
+
"flip_sin_to_cos": true,
|
31 |
+
"freq_shift": 0,
|
32 |
+
"global_pool_conditions": false,
|
33 |
+
"in_channels": 4,
|
34 |
+
"layers_per_block": 2,
|
35 |
+
"mid_block_scale_factor": 1,
|
36 |
+
"norm_eps": 1e-05,
|
37 |
+
"norm_num_groups": 32,
|
38 |
+
"num_class_embeds": null,
|
39 |
+
"only_cross_attention": false,
|
40 |
+
"projection_class_embeddings_input_dim": null,
|
41 |
+
"resnet_time_scale_shift": "default",
|
42 |
+
"sample_size": 32,
|
43 |
+
"upcast_attention": false,
|
44 |
+
"use_linear_projection": false
|
45 |
+
}
|
control_v1p_sd15_brightness.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9161c3825216e6baa45806fe9763df13ee7c60f0e12e693b7d4a00f039b1ba86
|
3 |
+
size 1445154814
|
control_v1p_sd15_brightness.yaml
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
model:
|
2 |
+
target: cldm.cldm.ControlLDM
|
3 |
+
params:
|
4 |
+
linear_start: 0.00085
|
5 |
+
linear_end: 0.0120
|
6 |
+
num_timesteps_cond: 1
|
7 |
+
log_every_t: 200
|
8 |
+
timesteps: 1000
|
9 |
+
first_stage_key: "jpg"
|
10 |
+
cond_stage_key: "txt"
|
11 |
+
control_key: "hint"
|
12 |
+
image_size: 64
|
13 |
+
channels: 4
|
14 |
+
cond_stage_trainable: false
|
15 |
+
conditioning_key: crossattn
|
16 |
+
monitor: val/loss_simple_ema
|
17 |
+
scale_factor: 0.18215
|
18 |
+
use_ema: False
|
19 |
+
only_mid_control: False
|
20 |
+
|
21 |
+
control_stage_config:
|
22 |
+
target: cldm.cldm.ControlNet
|
23 |
+
params:
|
24 |
+
image_size: 32 # unused
|
25 |
+
in_channels: 4
|
26 |
+
hint_channels: 3
|
27 |
+
model_channels: 320
|
28 |
+
attention_resolutions: [ 4, 2, 1 ]
|
29 |
+
num_res_blocks: 2
|
30 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
31 |
+
num_heads: 8
|
32 |
+
use_spatial_transformer: True
|
33 |
+
transformer_depth: 1
|
34 |
+
context_dim: 768
|
35 |
+
use_checkpoint: True
|
36 |
+
legacy: False
|
37 |
+
|
38 |
+
unet_config:
|
39 |
+
target: cldm.cldm.ControlledUnetModel
|
40 |
+
params:
|
41 |
+
image_size: 32 # unused
|
42 |
+
in_channels: 4
|
43 |
+
out_channels: 4
|
44 |
+
model_channels: 320
|
45 |
+
attention_resolutions: [ 4, 2, 1 ]
|
46 |
+
num_res_blocks: 2
|
47 |
+
channel_mult: [ 1, 2, 4, 4 ]
|
48 |
+
num_heads: 8
|
49 |
+
use_spatial_transformer: True
|
50 |
+
transformer_depth: 1
|
51 |
+
context_dim: 768
|
52 |
+
use_checkpoint: True
|
53 |
+
legacy: False
|
54 |
+
|
55 |
+
first_stage_config:
|
56 |
+
target: ldm.models.autoencoder.AutoencoderKL
|
57 |
+
params:
|
58 |
+
embed_dim: 4
|
59 |
+
monitor: val/rec_loss
|
60 |
+
ddconfig:
|
61 |
+
double_z: true
|
62 |
+
z_channels: 4
|
63 |
+
resolution: 256
|
64 |
+
in_channels: 3
|
65 |
+
out_ch: 3
|
66 |
+
ch: 128
|
67 |
+
ch_mult:
|
68 |
+
- 1
|
69 |
+
- 2
|
70 |
+
- 4
|
71 |
+
- 4
|
72 |
+
num_res_blocks: 2
|
73 |
+
attn_resolutions: []
|
74 |
+
dropout: 0.0
|
75 |
+
lossconfig:
|
76 |
+
target: torch.nn.Identity
|
77 |
+
|
78 |
+
cond_stage_config:
|
79 |
+
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|