linoyts HF staff commited on
Commit
b168eb1
1 Parent(s): 21abfab

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 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - edm-training
13
+ inference:
14
+ parameters:
15
+ scheduler: EulerDiscreteScheduler
16
+
17
+ widget:
18
+
19
+ - text: 'a <s0><s1> emoji dressed as an easter bunny'
20
+ output:
21
+ url:
22
+ "image_0.png"
23
+
24
+ - text: 'a <s0><s1> emoji dressed as an easter bunny'
25
+ output:
26
+ url:
27
+ "image_1.png"
28
+
29
+ - text: 'a <s0><s1> emoji dressed as an easter bunny'
30
+ output:
31
+ url:
32
+ "image_2.png"
33
+
34
+ - text: 'a <s0><s1> emoji dressed as an easter bunny'
35
+ output:
36
+ url:
37
+ "image_3.png"
38
+
39
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
40
+ instance_prompt: a <s0><s1> emoji
41
+ license: openrail++
42
+ ---
43
+
44
+ # SDXL LoRA DreamBooth - linoyts/huggy_dora_edm_v4_pivotal
45
+
46
+ <Gallery />
47
+
48
+ ## Model description
49
+
50
+ ### These are linoyts/huggy_dora_edm_v4_pivotal LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
51
+
52
+ ## Download model
53
+
54
+ ### Use it with UIs such as AUTOMATIC1111, Comfy UI, SD.Next, Invoke
55
+
56
+ - **LoRA**: download **[`huggy_dora_edm_v4_pivotal.safetensors` here 💾](/linoyts/huggy_dora_edm_v4_pivotal/blob/main/huggy_dora_edm_v4_pivotal.safetensors)**.
57
+ - Place it on your `models/Lora` folder.
58
+ - On AUTOMATIC1111, load the LoRA by adding `<lora:huggy_dora_edm_v4_pivotal:1>` to your prompt. On ComfyUI just [load it as a regular LoRA](https://comfyanonymous.github.io/ComfyUI_examples/lora/).
59
+ - *Embeddings*: download **[`huggy_dora_edm_v4_pivotal_emb.safetensors` here 💾](/linoyts/huggy_dora_edm_v4_pivotal/blob/main/huggy_dora_edm_v4_pivotal_emb.safetensors)**.
60
+ - Place it on it on your `embeddings` folder
61
+ - Use it by adding `huggy_dora_edm_v4_pivotal_emb` to your prompt. For example, `a huggy_dora_edm_v4_pivotal_emb emoji`
62
+ (you need both the LoRA and the embeddings as they were trained together for this LoRA)
63
+
64
+
65
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
66
+
67
+ ```py
68
+ from diffusers import AutoPipelineForText2Image
69
+ import torch
70
+ from huggingface_hub import hf_hub_download
71
+ from safetensors.torch import load_file
72
+
73
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
74
+ pipeline.load_lora_weights('linoyts/huggy_dora_edm_v4_pivotal', weight_name='pytorch_lora_weights.safetensors')
75
+ embedding_path = hf_hub_download(repo_id='linoyts/huggy_dora_edm_v4_pivotal', filename='huggy_dora_edm_v4_pivotal_emb.safetensors', repo_type="model")
76
+ state_dict = load_file(embedding_path)
77
+ pipeline.load_textual_inversion(state_dict["clip_l"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder, tokenizer=pipeline.tokenizer)
78
+ pipeline.load_textual_inversion(state_dict["clip_g"], token=["<s0>", "<s1>"], text_encoder=pipeline.text_encoder_2, tokenizer=pipeline.tokenizer_2)
79
+
80
+ image = pipeline('a <s0><s1> emoji dressed as an easter bunny').images[0]
81
+ ```
82
+
83
+ 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)
84
+
85
+ ## Trigger words
86
+
87
+ To trigger image generation of trained concept(or concepts) replace each concept identifier in you prompt with the new inserted tokens:
88
+
89
+ to trigger concept `TOK` → use `<s0><s1>` in your prompt
90
+
91
+
92
+
93
+ ## Details
94
+ All [Files & versions](/linoyts/huggy_dora_edm_v4_pivotal/tree/main).
95
+
96
+ 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).
97
+
98
+ LoRA for the text encoder was enabled. False.
99
+
100
+ Pivotal tuning was enabled: True.
101
+
102
+ Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
103
+
huggy_dora_edm_v4_pivotal.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:470122d17dceffa7c5b72bfee44d0d5e5fceb5f6ab86290b6c43749cfc4d3092
3
+ size 49448824
huggy_dora_edm_v4_pivotal_emb.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2c335e6fc39ad942c232d7c6c680cec7a57855eabc09b06baba061fa38b4484
3
+ size 16536
image_0.png ADDED

Git LFS Details

  • SHA256: c3d1267e9f8efc8e5d53785818466e540c430a1af44cb5b60cfa1a8a301cbf87
  • Pointer size: 132 Bytes
  • Size of remote file: 1.32 MB
image_1.png ADDED

Git LFS Details

  • SHA256: f26737bc9d042bfb6754523ca33eeaa201dd631daa092b1b86c5380edddb7a98
  • Pointer size: 132 Bytes
  • Size of remote file: 1.11 MB
image_2.png ADDED

Git LFS Details

  • SHA256: 98dce04c556414525bd568f07ea5ad795ef168e7fbc3a69f1641f44ae0eb8e50
  • Pointer size: 132 Bytes
  • Size of remote file: 1.57 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 sha256:84ff076213329547118a7591bbe6d4a43c234d2bced8642b31193b8db1d0ca9a
3
+ size 49363248