lfischbe commited on
Commit
216e2f3
·
verified ·
1 Parent(s): f3cd3c3

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,24 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ image-0.png filter=lfs diff=lfs merge=lfs -text
37
+ image-1.png filter=lfs diff=lfs merge=lfs -text
38
+ image-10.png filter=lfs diff=lfs merge=lfs -text
39
+ image-11.png filter=lfs diff=lfs merge=lfs -text
40
+ image-12.png filter=lfs diff=lfs merge=lfs -text
41
+ image-13.png filter=lfs diff=lfs merge=lfs -text
42
+ image-14.png filter=lfs diff=lfs merge=lfs -text
43
+ image-15.png filter=lfs diff=lfs merge=lfs -text
44
+ image-16.png filter=lfs diff=lfs merge=lfs -text
45
+ image-17.png filter=lfs diff=lfs merge=lfs -text
46
+ image-18.png filter=lfs diff=lfs merge=lfs -text
47
+ image-19.png filter=lfs diff=lfs merge=lfs -text
48
+ image-2.png filter=lfs diff=lfs merge=lfs -text
49
+ image-20.png filter=lfs diff=lfs merge=lfs -text
50
+ image-3.png filter=lfs diff=lfs merge=lfs -text
51
+ image-4.png filter=lfs diff=lfs merge=lfs -text
52
+ image-5.png filter=lfs diff=lfs merge=lfs -text
53
+ image-6.png filter=lfs diff=lfs merge=lfs -text
54
+ image-7.png filter=lfs diff=lfs merge=lfs -text
55
+ image-8.png filter=lfs diff=lfs merge=lfs -text
56
+ image-9.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - stable-diffusion-xl
4
+ - stable-diffusion-xl-diffusers
5
+ - text-to-image
6
+ - diffusers
7
+ - lora
8
+ - template:sd-lora
9
+ widget:
10
+ - text: a drawing of a woman's head with many different colored lines in the style
11
+ of <s0><s1>. The image is a colorful drawing of a person's face. The face is drawn
12
+ in a cartoon-like style with bright colors and intricate details. The person's
13
+ eyes are large and expressive, with a red nose and red lips. They are wearing
14
+ a blue shirt with a pink collar. The background of the drawing is white, and it
15
+ is filled with various shapes and patterns, including triangles, squares, and
16
+ rectangles in various colors such as green, yellow, red, and blue. The shapes
17
+ are arranged in a way that creates a sense of movement and energy, with some overlapping
18
+ and some standing out. The overall effect is one of chaos and confusion.
19
+ output:
20
+ url: image-0.png
21
+ - text: a painting of a woman's face with blue eyes in the style of <s0><s1>. painful
22
+ lightning shoots between the eyes.
23
+ output:
24
+ url: image-1.png
25
+ - text: a drawing of a person laying in bed with their eyes open in the style of <s0><s1>
26
+ output:
27
+ url: image-2.png
28
+ - text: a drawing of four people with different colored heads in the style of <s0><s1>
29
+ output:
30
+ url: image-3.png
31
+ - text: a drawing of a woman with a flower in her hair in the style of <s0><s1>
32
+ output:
33
+ url: image-4.png
34
+ - text: a painting with a woman's face and eye in the style of <s0><s1>
35
+ output:
36
+ url: image-5.png
37
+ - text: a drawing of a man in a room with a green and yellow wall in the style of
38
+ <s0><s1>
39
+ output:
40
+ url: image-6.png
41
+ - text: a painting of a face with stars on it in the style of <s0><s1>
42
+ output:
43
+ url: image-7.png
44
+ - text: a painting of a wave with a white circle around it in the style of <s0><s1>
45
+ output:
46
+ url: image-8.png
47
+ - text: a drawing of two birds on a post with flowers in the style of <s0><s1>
48
+ output:
49
+ url: image-9.png
50
+ - text: a drawing of a classroom with a teacher and students in the style of <s0><s1>
51
+ output:
52
+ url: image-10.png
53
+ - text: a painting of a bridge with a green tunnel in the style of <s0><s1>
54
+ output:
55
+ url: image-11.png
56
+ - text: a painting of a woman with blood on her face in the style of <s0><s1>
57
+ output:
58
+ url: image-12.png
59
+ - text: a drawing of a woman with a red flower in her head in the style of <s0><s1>
60
+ output:
61
+ url: image-13.png
62
+ - text: a black and white drawing of waves on a white background in the style of <s0><s1>
63
+ output:
64
+ url: image-14.png
65
+ - text: a drawing of a man and woman with a broken face in the style of <s0><s1>
66
+ output:
67
+ url: image-15.png
68
+ - text: a drawing of a colorful pattern of dots in the style of <s0><s1>
69
+ output:
70
+ url: image-16.png
71
+ - text: an abstract painting of a woman's face with blue eyes in the style of <s0><s1>
72
+ output:
73
+ url: image-17.png
74
+ - text: a painting of five women with different faces in the style of <s0><s1>
75
+ output:
76
+ url: image-18.png
77
+ - text: a painting of a woman with a sunburst behind her in the style of <s0><s1>
78
+ output:
79
+ url: image-19.png
80
+ - text: a painting of a woman with a green face and yellow eyes in the style of <s0><s1>
81
+ output:
82
+ url: image-20.png
83
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
84
+ instance_prompt: in the style of <s0><s1>
85
+ license: openrail++
86
+ ---
87
+
88
+ # SDXL LoRA DreamBooth - lfischbe/m1gr
89
+
90
+ <Gallery />
91
+
92
+ ## Model description
93
+
94
+ ### These are lfischbe/m1gr LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
95
+
96
+ ## Download model
97
+
98
+ ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
99
+
100
+ - **LoRA**: download **[`m1gr.safetensors` here 💾](/lfischbe/m1gr/blob/main/m1gr.safetensors)**.
101
+ - Place it on your `models/Lora` folder.
102
+ - On AUTOMATIC1111, load the LoRA by adding `<lora:m1gr:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
103
+ - *Embeddings*: download **[`m1gr_emb.safetensors` here 💾](/lfischbe/m1gr/blob/main/m1gr_emb.safetensors)**.
104
+ - Place it on it on your `embeddings` folder
105
+ - Use it by adding `m1gr_emb` to your prompt. For example, `in the style of m1gr_emb`
106
+ (you need both the LoRA and the embeddings as they were trained together for this LoRA)
107
+
108
+
109
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
110
+
111
+ ```py
112
+ from diffusers import AutoPipelineForText2Image
113
+ import torch
114
+ from huggingface_hub import hf_hub_download
115
+ from safetensors.torch import load_file
116
+
117
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
118
+ pipeline.load_lora_weights('lfischbe/m1gr', weight_name='pytorch_lora_weights.safetensors')
119
+ embedding_path = hf_hub_download(repo_id='lfischbe/m1gr', filename='m1gr_emb.safetensors' repo_type="model")
120
+ state_dict = load_file(embedding_path)
121
+ pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
122
+ pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
123
+
124
+ image = pipeline('in the style of <s0><s1>').images[0]
125
+ ```
126
+
127
+ For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
128
+
129
+ ## Trigger words
130
+
131
+ To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
132
+
133
+ to trigger concept `TOK` → use `<s0><s1>` in your prompt
134
+
135
+
136
+
137
+ ## Details
138
+ All [Files & versions](/lfischbe/m1gr/tree/main).
139
+
140
+ The weights were trained using [🧨 diffusers Advanced Dreambooth Training Script](https://github.com/huggingface/diffusers/blob/main/examples/advanced_diffusion_training/train_dreambooth_lora_sdxl_advanced.py).
141
+
142
+ LoRA for the text encoder was enabled. False.
143
+
144
+ Pivotal tuning was enabled: True.
145
+
146
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
147
+
image-0.png ADDED

Git LFS Details

  • SHA256: 436cde64faeec6544498ffa45f521e64862dc1a695bb9ff1edf6312ba611c2dc
  • Pointer size: 132 Bytes
  • Size of remote file: 1.69 MB
image-1.png ADDED

Git LFS Details

  • SHA256: 46c15c9871909cf975de21dcc3ca0f2ef7a6aa7ff8bf064e5e750b798db0494a
  • Pointer size: 132 Bytes
  • Size of remote file: 1.2 MB
image-10.png ADDED

Git LFS Details

  • SHA256: f5d133728864c57faf7bbe08081269e2c76f4ca5da5413bcddcb03878fd94382
  • Pointer size: 132 Bytes
  • Size of remote file: 1.52 MB
image-11.png ADDED

Git LFS Details

  • SHA256: 1965079bc99a1067abeccdad67f5a4cca943b5f33a0d0ac476b178944d76f7a0
  • Pointer size: 132 Bytes
  • Size of remote file: 1.15 MB
image-12.png ADDED

Git LFS Details

  • SHA256: eb5d834c18ed83f8c4a3426e549ee2a3b97856194fba75563c4c52e9120f2c28
  • Pointer size: 132 Bytes
  • Size of remote file: 1.28 MB
image-13.png ADDED

Git LFS Details

  • SHA256: 6f0681d92b1b6daa45d50f073a34ae4879f08fdd591d8ccf9344fcc0e67fd8b9
  • Pointer size: 132 Bytes
  • Size of remote file: 1.5 MB
image-14.png ADDED

Git LFS Details

  • SHA256: bde9548547c8d82fc358f1c99a3f7439f57c0e99e79a1d70aad82df31280e93c
  • Pointer size: 132 Bytes
  • Size of remote file: 1.48 MB
image-15.png ADDED

Git LFS Details

  • SHA256: e7f7eb24379d8d1284f5d4807cbdb32fac9a2ecb546cd88dbc5b550746588d44
  • Pointer size: 132 Bytes
  • Size of remote file: 1.29 MB
image-16.png ADDED

Git LFS Details

  • SHA256: 303176eb5538278b0fda8dfd53b25d12d77da11a38e29f8e020234cadfd2b8a5
  • Pointer size: 132 Bytes
  • Size of remote file: 1.69 MB
image-17.png ADDED

Git LFS Details

  • SHA256: 7960d544d86a1015b33bc51461f9a2e471d00698791efd2ce4478cc57fe757f5
  • Pointer size: 132 Bytes
  • Size of remote file: 1.47 MB
image-18.png ADDED

Git LFS Details

  • SHA256: 96df528ba7707140e0d87e9c59bf6a1d65217aacd27f284e1987524fb2e77224
  • Pointer size: 132 Bytes
  • Size of remote file: 1.42 MB
image-19.png ADDED

Git LFS Details

  • SHA256: 8c26ae648ae6c52447b333a48aa67178c0bc561420305c507a707a9833fb9538
  • Pointer size: 132 Bytes
  • Size of remote file: 1.67 MB
image-2.png ADDED

Git LFS Details

  • SHA256: a183a591d946130835c57de63c066a4a5594c1f959c18269537595db251b64cf
  • Pointer size: 132 Bytes
  • Size of remote file: 1.44 MB
image-20.png ADDED

Git LFS Details

  • SHA256: 2ee5da27eb06a5df064a1886dd778098526344fa464621f6518d57ba18a1d570
  • Pointer size: 132 Bytes
  • Size of remote file: 1.32 MB
image-3.png ADDED

Git LFS Details

  • SHA256: ae23bee4413228e5c56aa00233740d464ba06aace23c5aa8f2d3cc0028bc59a0
  • Pointer size: 132 Bytes
  • Size of remote file: 1.5 MB
image-4.png ADDED

Git LFS Details

  • SHA256: b62af236ccf6e13734fcf2b983e055e75ff6a50f70e798a2a1dea90dd1873cc6
  • Pointer size: 132 Bytes
  • Size of remote file: 1.37 MB
image-5.png ADDED

Git LFS Details

  • SHA256: 0c158808e961ca855dee7f04d920969708ccd2a20ba929f0db5b03c7add79475
  • Pointer size: 132 Bytes
  • Size of remote file: 1.46 MB
image-6.png ADDED

Git LFS Details

  • SHA256: 66e1d461e5e8e47387b7ebb2e10219300163b0365d9173414300342a57419e53
  • Pointer size: 132 Bytes
  • Size of remote file: 1.18 MB
image-7.png ADDED

Git LFS Details

  • SHA256: eb1e2b312494bbbaed7822b988b572268a8701499df9754256e96fccfd020258
  • Pointer size: 132 Bytes
  • Size of remote file: 1.55 MB
image-8.png ADDED

Git LFS Details

  • SHA256: 0af9652172aaf5e4cdfe24c5d729b2e5fe0d009a87de39ab704f454cde1daeb8
  • Pointer size: 132 Bytes
  • Size of remote file: 1.53 MB
image-9.png ADDED

Git LFS Details

  • SHA256: cc3dc9f5857f2711a3749683c859e36e249e3dd01e930c41f409256544771919
  • Pointer size: 132 Bytes
  • Size of remote file: 1.15 MB
logs/dreambooth-lora-sd-xl/1731001662.948938/events.out.tfevents.1731001662.r-lfischbe-autotrain-m1gr-zd6rx0fw-3b722-0cxs9.218.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a237a9176ddc2d09bf4e7d63b9ae3e16d874ff44dea0be3472c41b87371bea76
3
+ size 3567
logs/dreambooth-lora-sd-xl/1731001662.950264/hparams.yml ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ adam_beta1: 0.9
2
+ adam_beta2: 0.999
3
+ adam_epsilon: 1.0e-08
4
+ adam_weight_decay: 0.0001
5
+ adam_weight_decay_text_encoder: null
6
+ allow_tf32: false
7
+ cache_dir: null
8
+ cache_latents: true
9
+ caption_column: prompt
10
+ center_crop: false
11
+ checkpointing_steps: 100000
12
+ checkpoints_total_limit: null
13
+ class_data_dir: null
14
+ class_prompt: null
15
+ crops_coords_top_left_h: 0
16
+ crops_coords_top_left_w: 0
17
+ dataloader_num_workers: 0
18
+ dataset_config_name: null
19
+ dataset_name: ./856bd00c-e0db-4244-b2f4-279ef7491772
20
+ enable_xformers_memory_efficient_attention: false
21
+ gradient_accumulation_steps: 1
22
+ gradient_checkpointing: true
23
+ hub_model_id: null
24
+ hub_token: null
25
+ image_column: image
26
+ instance_data_dir: null
27
+ instance_prompt: in the style of <s0><s1>
28
+ learning_rate: 1.0
29
+ local_rank: -1
30
+ logging_dir: logs
31
+ lr_num_cycles: 1
32
+ lr_power: 1.0
33
+ lr_scheduler: constant
34
+ lr_warmup_steps: 0
35
+ max_grad_norm: 1.0
36
+ max_train_steps: 1500
37
+ mixed_precision: bf16
38
+ noise_offset: 0
39
+ num_class_images: 100
40
+ num_new_tokens_per_abstraction: 2
41
+ num_train_epochs: 72
42
+ num_validation_images: 4
43
+ optimizer: prodigy
44
+ output_dir: m1gr
45
+ pretrained_model_name_or_path: stabilityai/stable-diffusion-xl-base-1.0
46
+ pretrained_vae_model_name_or_path: madebyollin/sdxl-vae-fp16-fix
47
+ prior_generation_precision: null
48
+ prior_loss_weight: 1.0
49
+ prodigy_beta3: null
50
+ prodigy_decouple: true
51
+ prodigy_safeguard_warmup: true
52
+ prodigy_use_bias_correction: true
53
+ push_to_hub: false
54
+ rank: 32
55
+ repeats: 2
56
+ report_to: tensorboard
57
+ resolution: 1024
58
+ resume_from_checkpoint: null
59
+ revision: null
60
+ sample_batch_size: 4
61
+ scale_lr: false
62
+ seed: 42
63
+ snr_gamma: null
64
+ text_encoder_lr: 1.0
65
+ token_abstraction: TOK
66
+ train_batch_size: 2
67
+ train_text_encoder: false
68
+ train_text_encoder_frac: 1.0
69
+ train_text_encoder_ti: true
70
+ train_text_encoder_ti_frac: 0.5
71
+ use_8bit_adam: false
72
+ validation_epochs: 50
73
+ validation_prompt: null
74
+ variant: null
75
+ with_prior_preservation: false
logs/dreambooth-lora-sd-xl/events.out.tfevents.1731001662.r-lfischbe-autotrain-m1gr-zd6rx0fw-3b722-0cxs9.218.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2378d95e9cb3826597d4d5025f4aa1cbeabbb2e866ef1ebd07ff2a5637e878
3
+ size 125834
m1gr.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb9506c22cde8e2063fe882db2bada046c074d16a239eb855cc62c4c4872607e
3
+ size 186046568
m1gr_emb.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1e45ac34ce9dd86e190f86773cc5ffa3326bd36813ac0b3da1e92eca3f31544
3
+ size 16536
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a21dae02173f0d44d92d6385ee3abeb884dab36c5f7d592101be0671453013b
3
+ size 185963768