ViscoseBean commited on
Commit
90a1984
1 Parent(s): 1129ad3

Upload 4 files

Browse files
README.md CHANGED
@@ -1,3 +1,47 @@
1
  ---
2
- license: wtfpl
 
 
 
 
 
 
 
 
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