Hugging Face's logo

Nahrawy
/
controlnet-shadow-output

Text-to-Image
Diffusers
stable-diffusion
stable-diffusion-diffusers
controlnet
jax-diffusers-event
Model card Files Community
Nahrawy commited on
Commit
d2bc3b7
·
1 Parent(s): ab1fc28

End of training

Browse files
Files changed (10) hide show
  1. 1000/config.json +33 -0
  2. 1000/diffusion_flax_model.msgpack +3 -0
  3. 500/config.json +33 -0
  4. 500/diffusion_flax_model.msgpack +3 -0
  5. README.md +23 -0
  6. config.json +33 -0
  7. diffusion_flax_model.msgpack +3 -0
  8. image_control.png +0 -0
  9. images_0.png +0 -0
  10. images_1.png +0 -0
1000/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlaxControlNetModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "attention_head_dim": 8,
5
+ "block_out_channels": [
6
+ 320,
7
+ 640,
8
+ 1280,
9
+ 1280
10
+ ],
11
+ "conditioning_embedding_out_channels": [
12
+ 16,
13
+ 32,
14
+ 96,
15
+ 256
16
+ ],
17
+ "controlnet_conditioning_channel_order": "rgb",
18
+ "cross_attention_dim": 768,
19
+ "down_block_types": [
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "CrossAttnDownBlock2D",
23
+ "DownBlock2D"
24
+ ],
25
+ "dropout": 0.0,
26
+ "flip_sin_to_cos": true,
27
+ "freq_shift": 0,
28
+ "in_channels": 4,
29
+ "layers_per_block": 2,
30
+ "only_cross_attention": false,
31
+ "sample_size": 32,
32
+ "use_linear_projection": false
33
+ }
1000/diffusion_flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0d4e276e99e5e49ce479fa1fa180052bd9d049cd45fe7a8992665b26688fa8
3
+ size 1445128798
500/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlaxControlNetModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "attention_head_dim": 8,
5
+ "block_out_channels": [
6
+ 320,
7
+ 640,
8
+ 1280,
9
+ 1280
10
+ ],
11
+ "conditioning_embedding_out_channels": [
12
+ 16,
13
+ 32,
14
+ 96,
15
+ 256
16
+ ],
17
+ "controlnet_conditioning_channel_order": "rgb",
18
+ "cross_attention_dim": 768,
19
+ "down_block_types": [
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "CrossAttnDownBlock2D",
23
+ "DownBlock2D"
24
+ ],
25
+ "dropout": 0.0,
26
+ "flip_sin_to_cos": true,
27
+ "freq_shift": 0,
28
+ "in_channels": 4,
29
+ "layers_per_block": 2,
30
+ "only_cross_attention": false,
31
+ "sample_size": 32,
32
+ "use_linear_projection": false
33
+ }
500/diffusion_flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdf1b82d73364119f323b890fcf78ee19e2e0ef6aaa9d2b37637fc65ea4d4db0
3
+ size 1445128798
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: runwayml/stable-diffusion-v1-5
5
+ tags:
6
+ - stable-diffusion
7
+ - stable-diffusion-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - controlnet
11
+ - jax-diffusers-event
12
+ inference: true
13
+ ---
14
+
15
+ # controlnet- Nahrawy/controlnet-shadow-output
16
+
17
+ These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning. You can find some example images in the following.
18
+
19
+ prompt: a hollow wooden box and ribbed green ball in the air with shadows on the ground, light direction west+32, light elevation 25
20
+ ![images_0)](./images_0.png)
21
+ prompt: a hollow green cube and ribbed silver ball in the air and metallic cone with shadows on the ground, light direction east+34, light elevation 25
22
+ ![images_1)](./images_1.png)
23
+
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlaxControlNetModel",
3
+ "_diffusers_version": "0.17.0.dev0",
4
+ "attention_head_dim": 8,
5
+ "block_out_channels": [
6
+ 320,
7
+ 640,
8
+ 1280,
9
+ 1280
10
+ ],
11
+ "conditioning_embedding_out_channels": [
12
+ 16,
13
+ 32,
14
+ 96,
15
+ 256
16
+ ],
17
+ "controlnet_conditioning_channel_order": "rgb",
18
+ "cross_attention_dim": 768,
19
+ "down_block_types": [
20
+ "CrossAttnDownBlock2D",
21
+ "CrossAttnDownBlock2D",
22
+ "CrossAttnDownBlock2D",
23
+ "DownBlock2D"
24
+ ],
25
+ "dropout": 0.0,
26
+ "flip_sin_to_cos": true,
27
+ "freq_shift": 0,
28
+ "in_channels": 4,
29
+ "layers_per_block": 2,
30
+ "only_cross_attention": false,
31
+ "sample_size": 32,
32
+ "use_linear_projection": false
33
+ }
diffusion_flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c03d1c04b2179ff9d489883ae1a863e342d7c843d6b556d961c5cbf3e2c9d51
3
+ size 1445128798
image_control.png ADDED
images_0.png ADDED
images_1.png ADDED