ostris commited on
Commit
5389fa2
1 Parent(s): eb5996d

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. 1680148.jpeg +0 -0
  2. 1680193.jpeg +0 -0
  3. 1680194.jpeg +0 -0
  4. 1680197.jpeg +0 -0
  5. 1680210.jpeg +0 -0
  6. 1680230.jpeg +0 -0
  7. 1680232.jpeg +0 -0
  8. README.md +104 -0
  9. zoom_slider_v1.safetensors +3 -0
1680148.jpeg ADDED
1680193.jpeg ADDED
1680194.jpeg ADDED
1680197.jpeg ADDED
1680210.jpeg ADDED
1680230.jpeg ADDED
1680232.jpeg ADDED
README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: bespoke-lora-trained-license
4
+ license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
5
+ tags:
6
+ - text-to-image
7
+ - stable-diffusion
8
+ - lora
9
+ - diffusers
10
+ - template:sd-lora
11
+ - migrated
12
+ - portrait
13
+ - tool
14
+ - zoom
15
+ - slider
16
+
17
+ base_model: runwayml/stable-diffusion-v1-5
18
+ instance_prompt:
19
+ widget:
20
+ - text: 'photo of a woman, blonde hair, smiling, in the woods '
21
+ parameters:
22
+ negative_prompt: cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
23
+
24
+ output:
25
+ url: >-
26
+ 1680148.jpeg
27
+ - text: 'photo of a woman, red hair, smiling, in the woods '
28
+ parameters:
29
+ negative_prompt: cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
30
+
31
+ output:
32
+ url: >-
33
+ 1680193.jpeg
34
+ - text: 'photo of a woman, red hair, smiling, in the woods '
35
+ parameters:
36
+ negative_prompt: cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
37
+
38
+ output:
39
+ url: >-
40
+ 1680194.jpeg
41
+ - text: 'photo of a woman, red hair, smiling, in the woods '
42
+ parameters:
43
+ negative_prompt: cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
44
+
45
+ output:
46
+ url: >-
47
+ 1680197.jpeg
48
+ - text: 'photo of a woman, red hair, smiling, in the woods '
49
+ parameters:
50
+ negative_prompt: cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
51
+
52
+ output:
53
+ url: >-
54
+ 1680210.jpeg
55
+ - text: 'photo of a woman, red hair, smiling, in the woods '
56
+ parameters:
57
+ negative_prompt: cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
58
+
59
+ output:
60
+ url: >-
61
+ 1680230.jpeg
62
+ - text: 'photo of a woman, red hair, smiling, in the woods '
63
+ parameters:
64
+ negative_prompt: cartoon, cgi, render, illustration, painting, drawing, bad quality, grainy, low resolution
65
+
66
+ output:
67
+ url: >-
68
+ 1680232.jpeg
69
+
70
+ ---
71
+
72
+ # Zoom Slider - LoRA
73
+
74
+ <Gallery />
75
+
76
+
77
+
78
+
79
+
80
+ ## Model description
81
+
82
+ <ul><li><p>weight: <strong>-7.0 to 7.0</strong> </p></li><li><p>positive: <strong>zoom in (face close up)</strong></p></li><li><p>negative: <strong>zoom out (full body)</strong></p></li></ul><p></p><p>This is <strong>NOT</strong> perfect. I have tried to make this for a very long time using a dozen different methods and nothing worked. My slider training script was finally able to kick something out that is decently functional. I will continue to work on it because this is the slider I want more than anything else.</p><p></p><p>The slide in and out is not always smooth, it will hit points that "hang" where the clothing mostly changes for 1-3 weight steps without changing zoom, but it will break through if you keep pushing it. Let me know if you find any thing that can use improvement. </p>
83
+
84
+
85
+
86
+ ## Download model
87
+
88
+ Weights for this model are available in Safetensors format.
89
+
90
+ [Download](/ostris/zoom-slider-lora/tree/main) them in the Files & versions tab.
91
+
92
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
93
+
94
+ ```py
95
+ from diffusers import AutoPipelineForText2Image
96
+ import torch
97
+
98
+ pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
99
+ pipeline.load_lora_weights('ostris/zoom-slider-lora', weight_name='zoom_slider_v1.safetensors')
100
+ image = pipeline('photo of a woman, red hair, smiling, in the woods ').images[0]
101
+ ```
102
+
103
+ 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)
104
+
zoom_slider_v1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3737cff5b829595de0ae416c504d5e632e82b52270931d1b39aadfc12ea215e4
3
+ size 6865816