linoyts HF staff commited on
Commit
3c2880d
1 Parent(s): 9f100da

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ 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_2.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+
3
+ tags:
4
+ - stable-diffusion-xl
5
+ - stable-diffusion-xl-diffusers
6
+ - diffusers-training
7
+ - text-to-image
8
+ - diffusers
9
+ - dora
10
+ - template:sd-lora
11
+
12
+ widget:
13
+
14
+ - text: 'a <s0><s1> emoji dressed as an easter bunny'
15
+ output:
16
+ url:
17
+ "image_0.png"
18
+
19
+ - text: 'a <s0><s1> emoji dressed as an easter bunny'
20
+ output:
21
+ url:
22
+ "image_1.png"
23
+
24
+ - text: 'a <s0><s1> emoji dressed as an easter bunny'
25
+ output:
26
+ url:
27
+ "image_2.png"
28
+
29
+ - text: 'a <s0><s1> emoji dressed as an easter bunny'
30
+ output:
31
+ url:
32
+ "image_3.png"
33
+
34
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
35
+ instance_prompt: a <s0><s1> emoji
36
+ license: openrail++
37
+ ---
38
+
39
+ # SDXL LoRA DreamBooth - linoyts/huggy_dora_v2_pivotal
40
+
41
+ <Gallery />
42
+
43
+ ## Model description
44
+
45
+ ### These are linoyts/huggy_dora_v2_pivotal LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
46
+
47
+ ## Download model
48
+
49
+ ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
50
+
51
+ - **LoRA**: download **[`huggy_dora_v2_pivotal.safetensors` here 💾](/linoyts/huggy_dora_v2_pivotal/blob/main/huggy_dora_v2_pivotal.safetensors)**.
52
+ - Place it on your `models/Lora` folder.
53
+ - On AUTOMATIC1111, load the LoRA by adding `<lora:huggy_dora_v2_pivotal:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
54
+ - *Embeddings*: download **[`huggy_dora_v2_pivotal_emb.safetensors` here 💾](/linoyts/huggy_dora_v2_pivotal/blob/main/huggy_dora_v2_pivotal_emb.safetensors)**.
55
+ - Place it on it on your `embeddings` folder
56
+ - Use it by adding `huggy_dora_v2_pivotal_emb` to your prompt. For example, `a huggy_dora_v2_pivotal_emb emoji`
57
+ (you need both the LoRA and the embeddings as they were trained together for this LoRA)
58
+
59
+
60
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
61
+
62
+ ```py
63
+ from diffusers import AutoPipelineForText2Image
64
+ import torch
65
+ from huggingface_hub import hf_hub_download
66
+ from safetensors.torch import load_file
67
+
68
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
69
+ pipeline.load_lora_weights('linoyts/huggy_dora_v2_pivotal', weight_name='pytorch_lora_weights.safetensors')
70
+ embedding_path = hf_hub_download(repo_id='linoyts/huggy_dora_v2_pivotal', filename='huggy_dora_v2_pivotal_emb.safetensors', repo_type="model")
71
+ state_dict = load_file(embedding_path)
72
+ pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
73
+ pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
74
+
75
+ image = pipeline('a <s0><s1> emoji dressed as an easter bunny').images[0]
76
+ ```
77
+
78
+ 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)
79
+
80
+ ## Trigger words
81
+
82
+ To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
83
+
84
+ to trigger concept `TOK` → use `<s0><s1>` in your prompt
85
+
86
+
87
+
88
+ ## Details
89
+ All [Files & versions](/linoyts/huggy_dora_v2_pivotal/tree/main).
90
+
91
+ 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).
92
+
93
+ LoRA for the text encoder was enabled. False.
94
+
95
+ Pivotal tuning was enabled: True.
96
+
97
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
98
+
huggy_dora_v2_pivotal.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:688515a41e4e220821809ef3c84d2d90d120a55e6673bedc78caa05dc4078fe1
3
+ size 188798032
huggy_dora_v2_pivotal_emb.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e8d96a86d236311fcc773b5220a8eb2a6135277ae0d7ed85bc3766fe263eb6d
3
+ size 16536
image_0.png ADDED

Git LFS Details

  • SHA256: 63c0b0e70745e6254310d2b527bf76ebe283529a2b9ed3729e82ef376064938e
  • Pointer size: 132 Bytes
  • Size of remote file: 1.6 MB
image_1.png ADDED

Git LFS Details

  • SHA256: dcb8b95184121dd7213520819e30d5fb2ae9cdd1bb187ca3b622aca4b5517030
  • Pointer size: 132 Bytes
  • Size of remote file: 1.39 MB
image_2.png ADDED

Git LFS Details

  • SHA256: cb21c98217d0cf90372be9ecc913a9f659254bd2afacf7a6cfdb2925a3534abb
  • Pointer size: 132 Bytes
  • Size of remote file: 1.55 MB
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:d3e75ea9c6ddff17dfe4df449354ea7dc05b6876dccc4dc54758d738fed84626
3
+ size 188712456