Hugging Face's logo

jiang0203
/
fine_tune_v3

Text-to-Image
Diffusers
Safetensors
stable-diffusion
stable-diffusion-diffusers
controlnet
diffusers-training
Model card Files Community
jiang0203 commited on
Commit
eaecaa8
·
verified ·
1 Parent(s): 233691a

End of training

Browse files
Files changed (24) hide show
  1. README.md +45 -0
  2. checkpoint-10000/controlnet/config.json +52 -0
  3. checkpoint-10000/controlnet/diffusion_pytorch_model.safetensors +3 -0
  4. checkpoint-10000/optimizer.bin +3 -0
  5. checkpoint-10000/random_states_0.pkl +3 -0
  6. checkpoint-10000/scaler.pt +3 -0
  7. checkpoint-10000/scheduler.bin +3 -0
  8. checkpoint-15000/controlnet/config.json +52 -0
  9. checkpoint-15000/controlnet/diffusion_pytorch_model.safetensors +3 -0
  10. checkpoint-15000/optimizer.bin +3 -0
  11. checkpoint-15000/random_states_0.pkl +3 -0
  12. checkpoint-15000/scaler.pt +3 -0
  13. checkpoint-15000/scheduler.bin +3 -0
  14. checkpoint-5000/controlnet/config.json +52 -0
  15. checkpoint-5000/controlnet/diffusion_pytorch_model.safetensors +3 -0
  16. checkpoint-5000/optimizer.bin +3 -0
  17. checkpoint-5000/random_states_0.pkl +3 -0
  18. checkpoint-5000/scaler.pt +3 -0
  19. checkpoint-5000/scheduler.bin +3 -0
  20. config.json +52 -0
  21. diffusion_pytorch_model.safetensors +3 -0
  22. image_control.png +0 -0
  23. images_0.png +0 -0
  24. images_1.png +0 -0
README.md ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: runwayml/stable-diffusion-v1-5
3
+ library_name: diffusers
4
+ license: creativeml-openrail-m
5
+ tags:
6
+ - stable-diffusion
7
+ - stable-diffusion-diffusers
8
+ - text-to-image
9
+ - diffusers
10
+ - controlnet
11
+ - diffusers-training
12
+ inference: true
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the training script had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+
19
+ # controlnet-jiang0203/fine_tune_v3
20
+
21
+ These are controlnet weights trained on runwayml/stable-diffusion-v1-5 with new type of conditioning.
22
+ You can find some example images below.
23
+
24
+ prompt: The screenshot is very likely an editor app. You can see a functionality to edit or create content. You may notice a web view located at the center area which you can do click. A web view is a component that displays website content.
25
+ ![images_0)](./images_0.png)
26
+ prompt: The interface looks like a modal app. You can see a popup window with additional content. You can find a text placed at the center area of the screen.
27
+ ![images_1)](./images_1.png)
28
+
29
+
30
+
31
+ ## Intended uses & limitations
32
+
33
+ #### How to use
34
+
35
+ ```python
36
+ # TODO: add an example code snippet for running this diffusion pipeline
37
+ ```
38
+
39
+ #### Limitations and bias
40
+
41
+ [TODO: provide examples of latent issues and potential remediations]
42
+
43
+ ## Training details
44
+
45
+ [TODO: describe the data used to train the model]
checkpoint-10000/controlnet/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "/home/jiang/BoostingGUI/fine_tune_v2",
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
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "class_embed_type": null,
17
+ "conditioning_channels": 3,
18
+ "conditioning_embedding_out_channels": [
19
+ 16,
20
+ 32,
21
+ 96,
22
+ 256
23
+ ],
24
+ "controlnet_conditioning_channel_order": "rgb",
25
+ "cross_attention_dim": 768,
26
+ "down_block_types": [
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "DownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "global_pool_conditions": false,
38
+ "in_channels": 4,
39
+ "layers_per_block": 2,
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
+ "projection_class_embeddings_input_dim": null,
48
+ "resnet_time_scale_shift": "default",
49
+ "transformer_layers_per_block": 1,
50
+ "upcast_attention": false,
51
+ "use_linear_projection": false
52
+ }
checkpoint-10000/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16bb1e0f9cef0da9561f0ef24a6589b6ec37e1454cc464ddbcc17bb94acaec00
3
+ size 1445157120
checkpoint-10000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4df7d9053d1b57b4303f44f617e818370318ac5050e5b42064ac84bc54f83d2
3
+ size 725253818
checkpoint-10000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c58bb235cd4a0c2c7a3cbc10add95cb40f3ce56c1312c84fbd2d0145ecdfd9
3
+ size 14344
checkpoint-10000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d49367aa0f19981d0484e3ef5c1b009e6bdd8e5c0d8ef08f2f8d235b9f843816
3
+ size 988
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-15000/controlnet/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "/home/jiang/BoostingGUI/fine_tune_v2",
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
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "class_embed_type": null,
17
+ "conditioning_channels": 3,
18
+ "conditioning_embedding_out_channels": [
19
+ 16,
20
+ 32,
21
+ 96,
22
+ 256
23
+ ],
24
+ "controlnet_conditioning_channel_order": "rgb",
25
+ "cross_attention_dim": 768,
26
+ "down_block_types": [
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "DownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "global_pool_conditions": false,
38
+ "in_channels": 4,
39
+ "layers_per_block": 2,
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
+ "projection_class_embeddings_input_dim": null,
48
+ "resnet_time_scale_shift": "default",
49
+ "transformer_layers_per_block": 1,
50
+ "upcast_attention": false,
51
+ "use_linear_projection": false
52
+ }
checkpoint-15000/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f9a7ed0badf640e7bc6413ac1ecee5ccd19c6ec75d5c3c0563dd85703c0063
3
+ size 1445157120
checkpoint-15000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca9a71c8e23e388ba24fd51e5ad729d9521494c6529bfbc2aed25158b1b5cf3
3
+ size 725253818
checkpoint-15000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeac5ecac2b4f6e218d0278fe633bfd4145d33869cfca90d66417f88153224e7
3
+ size 14344
checkpoint-15000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2491380f0b55e3e8cbfec1654220a94cf6d79d50cd1b1e51dfe593c04a274cb9
3
+ size 988
checkpoint-15000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f8cb1c00499c9a11be98e1d3df14acb1c3f608844e19988fc0598608b723e0
3
+ size 1000
checkpoint-5000/controlnet/config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "/home/jiang/BoostingGUI/fine_tune_v2",
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
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "class_embed_type": null,
17
+ "conditioning_channels": 3,
18
+ "conditioning_embedding_out_channels": [
19
+ 16,
20
+ 32,
21
+ 96,
22
+ 256
23
+ ],
24
+ "controlnet_conditioning_channel_order": "rgb",
25
+ "cross_attention_dim": 768,
26
+ "down_block_types": [
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "DownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "global_pool_conditions": false,
38
+ "in_channels": 4,
39
+ "layers_per_block": 2,
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
+ "projection_class_embeddings_input_dim": null,
48
+ "resnet_time_scale_shift": "default",
49
+ "transformer_layers_per_block": 1,
50
+ "upcast_attention": false,
51
+ "use_linear_projection": false
52
+ }
checkpoint-5000/controlnet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f01b0eb6df9212aefe76699b071eff3af38da48de38f70c7cb156265d2c41bbd
3
+ size 1445157120
checkpoint-5000/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1146fa83596b1a06476b5e975c1a0161be5f335a62a0e0bab6756f82d44e531c
3
+ size 725253818
checkpoint-5000/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00729efb0598f5bed786900dbde72e3a976826c4b875e3d1bd13f72f43c82ca4
3
+ size 14408
checkpoint-5000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41216328ab75de937007afb04d76156949bedb908461001a451c8991c2ba8cca
3
+ size 988
checkpoint-5000/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:920333155b08e76154b89a85170c320833074db7b84649a9cfe79fd10b6bf2d9
3
+ size 1000
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "ControlNetModel",
3
+ "_diffusers_version": "0.30.0.dev0",
4
+ "_name_or_path": "/home/jiang/BoostingGUI/fine_tune_v2",
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
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "class_embed_type": null,
17
+ "conditioning_channels": 3,
18
+ "conditioning_embedding_out_channels": [
19
+ 16,
20
+ 32,
21
+ 96,
22
+ 256
23
+ ],
24
+ "controlnet_conditioning_channel_order": "rgb",
25
+ "cross_attention_dim": 768,
26
+ "down_block_types": [
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "CrossAttnDownBlock2D",
30
+ "DownBlock2D"
31
+ ],
32
+ "downsample_padding": 1,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "global_pool_conditions": false,
38
+ "in_channels": 4,
39
+ "layers_per_block": 2,
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
+ "projection_class_embeddings_input_dim": null,
48
+ "resnet_time_scale_shift": "default",
49
+ "transformer_layers_per_block": 1,
50
+ "upcast_attention": false,
51
+ "use_linear_projection": false
52
+ }
diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d3f39b3f3291c109472193e1bbfb36f2fff4754ffca2fb17d597e7af2b7124d
3
+ size 1445157120
image_control.png ADDED
images_0.png ADDED
images_1.png ADDED