multimodalart HF staff commited on
Commit
505ffe2
1 Parent(s): 24fb2a9

Upload folder using huggingface_hub

Browse files
4449092.jpeg ADDED
4449094.jpeg ADDED
4449095.jpeg ADDED
4449100.jpeg ADDED
4449312.jpeg ADDED
EnvyBetterHiresFixXL01.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930e286cfdc8562fd1a155a141cf9257fb4fd35225f674479fc218d4afce4823
3
+ size 46702144
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: bespoke-lora-trained-license
4
+ license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Sell&allowDerivatives=True&allowDifferentLicense=True
5
+ tags:
6
+ - text-to-image
7
+ - stable-diffusion
8
+ - lora
9
+ - diffusers
10
+ - template:sd-lora
11
+ - vibrant colors
12
+ - style
13
+ - hires fix
14
+ - detail
15
+ - quality up
16
+ - sharpness
17
+
18
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
19
+ instance_prompt:
20
+ widget:
21
+ - text: ' '
22
+ output:
23
+ url: >-
24
+ 4449094.jpeg
25
+ - text: ' '
26
+ output:
27
+ url: >-
28
+ 4449095.jpeg
29
+ - text: ' '
30
+ output:
31
+ url: >-
32
+ 4449092.jpeg
33
+ - text: ' '
34
+ output:
35
+ url: >-
36
+ 4449100.jpeg
37
+ - text: 'photograph, cinematic color grading, 1girl, woman, beautiful, Industrial loft with skyline view in a empty fantasy topia outside of time, masterpiece'
38
+ output:
39
+ url: >-
40
+ 4449312.jpeg
41
+
42
+ ---
43
+
44
+ # Envy Better Hires Fix XL 01
45
+
46
+ <Gallery />
47
+
48
+
49
+
50
+
51
+
52
+ ## Model description
53
+
54
+ <p>Adds contrast, detail, and quality improvements to hires fix. Improves hands a bit. Gives more realistic skin textures on photorealistic models.</p><h3 id="heading-330">Important generation notes:</h3><p>In the example images, this LoRA was only enabled during the Hires Fix step. I've had very good results enabling it for both passes (in which case it makes generations more dramatic and vibrant), but it does alter composition somewhat, which makes direct comparison harder.</p><p>If you want to run this LoRA during your hires fix only, you can download this a1111 extension here:</p><p><a target="_blank" rel="ugc" href="https://github.com/cheald/sd-webui-loractl">https://github.com/cheald/sd-webui-loractl</a></p><p>...and add the LoRA to your positive prompt like this: &lt;lora:EnvyBetterHiresFixXL01:0:hr=1&gt;</p><p>(Or just add it like a normal LoRA to use it during both passes.)</p>
55
+
56
+
57
+
58
+ ## Download model
59
+
60
+ Weights for this model are available in Safetensors format.
61
+
62
+ [Download](/e-n-v-y/envy-better-hires-fix-xl-01/tree/main) them in the Files & versions tab.
63
+
64
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
65
+
66
+ ```py
67
+ from diffusers import AutoPipelineForText2Image
68
+ import torch
69
+
70
+ pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda')
71
+ pipeline.load_lora_weights('e-n-v-y/envy-better-hires-fix-xl-01', weight_name='EnvyBetterHiresFixXL01.safetensors')
72
+ image = pipeline('photograph, cinematic color grading, 1girl, woman, beautiful, Industrial loft with skyline view in a empty fantasy topia outside of time, masterpiece').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
+