linoyts HF staff commited on
Commit
f030071
1 Parent(s): c027499

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+
11
+ - text: 'a <s0><s1> emoji dressed as yoda'
12
+ output:
13
+ url:
14
+ "image_0.png"
15
+
16
+ - text: 'a <s0><s1> emoji dressed as yoda'
17
+ output:
18
+ url:
19
+ "image_1.png"
20
+
21
+ - text: 'a <s0><s1> emoji dressed as yoda'
22
+ output:
23
+ url:
24
+ "image_2.png"
25
+
26
+ - text: 'a <s0><s1> emoji dressed as yoda'
27
+ output:
28
+ url:
29
+ "image_3.png"
30
+
31
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
32
+ instance_prompt: a <s0><s1> emoji
33
+ license: openrail++
34
+ ---
35
+
36
+ # SDXL LoRA DreamBooth - linoyts/huggy_dora_pivotal_1_repeats_v6
37
+
38
+ <Gallery />
39
+
40
+ ## Model description
41
+
42
+ ### These are linoyts/huggy_dora_pivotal_1_repeats_v6 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
43
+
44
+ ## Download model
45
+
46
+ ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
47
+
48
+ - **LoRA**: download **[`huggy_dora_pivotal_1_repeats_v6.safetensors` here 💾](/linoyts/huggy_dora_pivotal_1_repeats_v6/blob/main/huggy_dora_pivotal_1_repeats_v6.safetensors)**.
49
+ - Place it on your `models/Lora` folder.
50
+ - On AUTOMATIC1111, load the LoRA by adding `<lora:huggy_dora_pivotal_1_repeats_v6:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
51
+ - *Embeddings*: download **[`huggy_dora_pivotal_1_repeats_v6_emb.safetensors` here 💾](/linoyts/huggy_dora_pivotal_1_repeats_v6/blob/main/huggy_dora_pivotal_1_repeats_v6_emb.safetensors)**.
52
+ - Place it on it on your `embeddings` folder
53
+ - Use it by adding `huggy_dora_pivotal_1_repeats_v6_emb` to your prompt. For example, `a huggy_dora_pivotal_1_repeats_v6_emb emoji`
54
+ (you need both the LoRA and the embeddings as they were trained together for this LoRA)
55
+
56
+
57
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
58
+
59
+ ```py
60
+ from diffusers import AutoPipelineForText2Image
61
+ import torch
62
+ from huggingface_hub import hf_hub_download
63
+ from safetensors.torch import load_file
64
+
65
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
66
+ pipeline.load_lora_weights('linoyts/huggy_dora_pivotal_1_repeats_v6', weight_name='pytorch_lora_weights.safetensors')
67
+ embedding_path = hf_hub_download(repo_id='linoyts/huggy_dora_pivotal_1_repeats_v6', filename='huggy_dora_pivotal_1_repeats_v6_emb.safetensors', repo_type="model")
68
+ state_dict = load_file(embedding_path)
69
+ pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
70
+ pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
71
+
72
+ image = pipeline('a <s0><s1> emoji dressed as yoda').images[0]
73
+ ```
74
+
75
+ 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)
76
+
77
+ ## Trigger words
78
+
79
+ To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
80
+
81
+ to trigger concept `TOK` → use `<s0><s1>` in your prompt
82
+
83
+
84
+
85
+ ## Details
86
+ All [Files & versions](/linoyts/huggy_dora_pivotal_1_repeats_v6/tree/main).
87
+
88
+ 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).
89
+
90
+ LoRA for the text encoder was enabled. False.
91
+
92
+ Pivotal tuning was enabled: True.
93
+
94
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
95
+
huggy_dora_pivotal_1_repeats_v6.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afc06fa74fec4c533933593a5964f1d5643ef321a84e917990bfa3bb8eb074b8
3
+ size 189279336
huggy_dora_pivotal_1_repeats_v6_emb.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e146f1bbf3b4406ddd32506fc0718f62b1452dbf042a0beabec725d6ae3cddee
3
+ size 16536
image_0.png ADDED

Git LFS Details

  • SHA256: 32fdb1e75f3b474e96a8e06814c474dbc3c90d118b78e1ed0fdae0537e90de3e
  • Pointer size: 132 Bytes
  • Size of remote file: 1.21 MB
image_1.png ADDED

Git LFS Details

  • SHA256: e2a1dcc763ef1d7ebd51050d02a8bc37b8dd48149bac848dacdbf8c2ad7cceed
  • Pointer size: 132 Bytes
  • Size of remote file: 1.11 MB
image_2.png ADDED
image_3.png ADDED
pytorch_lora_weights.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffa376ebf795c03f011aa466f7ae8e25855d3d0eedf0c3eef51cd3fdc63a08dc
3
+ size 189193768