IUseAMouse commited on
Commit
c35c070
1 Parent(s): 7348ff2

End of training

Browse files
README.md ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ license: creativeml-openrail-m
4
+ base_model: CompVis/stable-diffusion-v1-4
5
+ datasets:
6
+ - IUseAMouse/PointConImages
7
+ tags:
8
+ - stable-diffusion
9
+ - stable-diffusion-diffusers
10
+ - text-to-image
11
+ - diffusers
12
+ inference: true
13
+ ---
14
+
15
+ # Text-to-image finetuning - IUseAMouse/PointConImageModel
16
+
17
+ This pipeline was finetuned from **CompVis/stable-diffusion-v1-4** on the **IUseAMouse/PointConImages** dataset. Below are some example images generated with the finetuned pipeline using the following prompts: ['Un patron donne un dossier à un employé']:
18
+
19
+ ![val_imgs_grid](./val_imgs_grid.png)
20
+
21
+
22
+ ## Pipeline usage
23
+
24
+ You can use the pipeline like so:
25
+
26
+ ```python
27
+ from diffusers import DiffusionPipeline
28
+ import torch
29
+
30
+ pipeline = DiffusionPipeline.from_pretrained("IUseAMouse/PointConImageModel", torch_dtype=torch.float16)
31
+ prompt = "Un patron donne un dossier à un employé"
32
+ image = pipeline(prompt).images[0]
33
+ image.save("my_image.png")
34
+ ```
35
+
36
+ ## Training info
37
+
38
+ These are the key hyperparameters used during training:
39
+
40
+ * Epochs: 60
41
+ * Learning rate: 1e-05
42
+ * Batch size: 1
43
+ * Gradient accumulation steps: 4
44
+ * Image resolution: 512
45
+ * Mixed-precision: fp16
46
+
47
+
48
+ More information on all the CLI arguments and the environment are available on your [`wandb` run page](https://wandb.ai/acadys/text2image-fine-tune/runs/cpxo8qcw).
checkpoint-500/optimizer.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e325bbaac4ab436cd2678ba330c3d5e8f0360571e93a6120e101d8cdbcf0904
3
+ size 6876749715
checkpoint-500/random_states_0.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b39c50c894ae1a29405b25cc64a4fcfcbfda7157a12499e70411e3a0b4fe45c
3
+ size 14727
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f196a54202bb4ba1220e8c59f42f9cda0702d68ea83147d814c2fb2f36b8f2
3
+ size 557
checkpoint-500/scheduler.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab20ead000e6ae60e9a32d69fb1fb976d10dba2a065da680293a8202053a1975
3
+ size 563
checkpoint-500/unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
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
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "reverse_transformer_layers_per_block": null,
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
checkpoint-500/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15be1b597e3999651fc385fb689dd6e62fcce26e6042605ba232ed8db62df47c
3
+ size 3438167536
checkpoint-500/unet_ema/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "decay": 0.9999,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
33
+ "dual_cross_attention": false,
34
+ "encoder_hid_dim": null,
35
+ "encoder_hid_dim_type": null,
36
+ "flip_sin_to_cos": true,
37
+ "freq_shift": 0,
38
+ "in_channels": 4,
39
+ "inv_gamma": 1.0,
40
+ "layers_per_block": 2,
41
+ "mid_block_only_cross_attention": null,
42
+ "mid_block_scale_factor": 1,
43
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
44
+ "min_decay": 0.0,
45
+ "norm_eps": 1e-05,
46
+ "norm_num_groups": 32,
47
+ "num_attention_heads": null,
48
+ "num_class_embeds": null,
49
+ "only_cross_attention": false,
50
+ "optimization_step": 500,
51
+ "out_channels": 4,
52
+ "power": 0.6666666666666666,
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": 64,
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": false,
72
+ "update_after_step": 0,
73
+ "use_ema_warmup": false,
74
+ "use_linear_projection": false
75
+ }
checkpoint-500/unet_ema/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f174ddc6db00786ee8cb4ac1e4e3b91bfe30949acaac44892662236c940fcb1b
3
+ size 3438167536
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPImageProcessor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
model_index.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "requires_safety_checker": true,
10
+ "safety_checker": [
11
+ "stable_diffusion",
12
+ "StableDiffusionSafetyChecker"
13
+ ],
14
+ "scheduler": [
15
+ "diffusers",
16
+ "PNDMScheduler"
17
+ ],
18
+ "text_encoder": [
19
+ "transformers",
20
+ "CLIPTextModel"
21
+ ],
22
+ "tokenizer": [
23
+ "transformers",
24
+ "CLIPTokenizer"
25
+ ],
26
+ "unet": [
27
+ "diffusers",
28
+ "UNet2DConditionModel"
29
+ ],
30
+ "vae": [
31
+ "diffusers",
32
+ "AutoencoderKL"
33
+ ]
34
+ }
safety_checker/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/root/.cache/huggingface/hub/models--CompVis--stable-diffusion-v1-4/snapshots/133a221b8aa7292a167afc5127cb63fb5005638b/safety_checker",
3
+ "architectures": [
4
+ "StableDiffusionSafetyChecker"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "intermediate_size": 3072,
14
+ "model_type": "clip_text_model",
15
+ "num_attention_heads": 12
16
+ },
17
+ "torch_dtype": "float32",
18
+ "transformers_version": "4.34.1",
19
+ "vision_config": {
20
+ "dropout": 0.0,
21
+ "hidden_size": 1024,
22
+ "intermediate_size": 4096,
23
+ "model_type": "clip_vision_model",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "patch_size": 14
27
+ }
28
+ }
safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
3
+ size 1215979664
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "epsilon",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "timestep_spacing": "leading",
14
+ "trained_betas": null
15
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "quick_gelu",
11
+ "hidden_size": 768,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.34.1",
24
+ "vocab_size": 49408
25
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:660c6f5b1abae9dc498ac2d21e1347d2abdb0cf6c0c0c8576cd796491d9a6cdd
3
+ size 246144152
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
30
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
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
+ "attention_type": "default",
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": null,
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 768,
23
+ "cross_attention_norm": null,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "downsample_padding": 1,
31
+ "dropout": 0.0,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "encoder_hid_dim_type": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
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
+ "out_channels": 4,
48
+ "projection_class_embeddings_input_dim": null,
49
+ "resnet_out_scale_factor": 1.0,
50
+ "resnet_skip_time_act": false,
51
+ "resnet_time_scale_shift": "default",
52
+ "reverse_transformer_layers_per_block": null,
53
+ "sample_size": 64,
54
+ "time_cond_proj_dim": null,
55
+ "time_embedding_act_fn": null,
56
+ "time_embedding_dim": null,
57
+ "time_embedding_type": "positional",
58
+ "timestep_post_act": null,
59
+ "transformer_layers_per_block": 1,
60
+ "up_block_types": [
61
+ "UpBlock2D",
62
+ "CrossAttnUpBlock2D",
63
+ "CrossAttnUpBlock2D",
64
+ "CrossAttnUpBlock2D"
65
+ ],
66
+ "upcast_attention": false,
67
+ "use_linear_projection": false
68
+ }
unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ada6fdc31e02241e48b8cf3157c88333fd12dff2aaa658e138d504642b30037
3
+ size 3438167536
vae/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.22.0.dev0",
4
+ "_name_or_path": "CompVis/stable-diffusion-v1-4",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "force_upcast": true,
19
+ "in_channels": 3,
20
+ "latent_channels": 4,
21
+ "layers_per_block": 2,
22
+ "norm_num_groups": 32,
23
+ "out_channels": 3,
24
+ "sample_size": 512,
25
+ "scaling_factor": 0.18215,
26
+ "up_block_types": [
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D",
30
+ "UpDecoderBlock2D"
31
+ ]
32
+ }
vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
3
+ size 167335342
val_imgs_grid.png ADDED