Keltezaa commited on
Commit
58ec266
Β·
verified Β·
1 Parent(s): ffd2b87

Upload folder using huggingface_hub

Browse files
58122706.jpeg ADDED
58122737.jpeg ADDED
58122811.jpeg ADDED
58122962.jpeg ADDED
58122995.jpeg ADDED
AliLarter_flux_lora_v5.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78be144f46c1a0f7d45534dadfcc1933c76759a1d8ccf72f160151183e230e5e
3
+ size 171969416
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: bespoke-lora-trained-license
4
+ license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=RentCivit&allowDerivatives=False&allowDifferentLicense=True
5
+ tags:
6
+ - text-to-image
7
+ - stable-diffusion
8
+ - lora
9
+ - diffusers
10
+ - template:sd-lora
11
+ - migrated
12
+ - photorealistic
13
+ - woman
14
+ - actress
15
+ - celebrity
16
+ - girls
17
+ - realistic
18
+ - celebrity,
19
+
20
+ base_model: black-forest-labs/FLUX.1-dev
21
+ instance_prompt: ohwx
22
+ widget:
23
+ - text: 'Breathtaking over the shoulder shot photography of ohwx looking at viewer, imperfections, necklace, looking at viewer, eyelashes, fine hair detail, entire hairstyle visible, perfect eyes with iris pattern, sensual lips, nose, (perfectly sharp:1.3), realistic textures, (deep focus:1.5), 8k uhd, dslr, ultra high quality image, film grain, Fujifilm XT3'
24
+ parameters:
25
+ negative_prompt: AliLarter_flux_lora_v5_Weight-1.00
26
+
27
+ output:
28
+ url: >-
29
+ 58122706.jpeg
30
+ - text: 'Breathtaking over the shoulder shot photography of ohwx looking at viewer, imperfections, necklace, looking at viewer, eyelashes, fine hair detail, entire hairstyle visible, perfect eyes with iris pattern, sensual lips, nose, (perfectly sharp:1.3), realistic textures, (deep focus:1.5), 8k uhd, dslr, ultra high quality image, film grain, Fujifilm XT3'
31
+ parameters:
32
+ negative_prompt: AliLarter_flux_lora_v5_Weight-1.00
33
+
34
+ output:
35
+ url: >-
36
+ 58122737.jpeg
37
+ - text: 'Breathtaking photography of ohwx woman with ultra narrow waist. A close-up portrait of a young woman with a vibrant pink and purple hairstyle. She wears a black choker necklace with a teardrop-shaped pendant. Her makeup is bold and dramatic, featuring dark eyeliner and mascara. The background is a checkered pattern of alternating dark and light shades, creating a visually striking contrast. The image style is contemporary and edgy, emphasizing the subject''s unique and rebellious appearance., emphasizing the woman''s form and the natural beauty of the beach. A candid photo shot of a young woman. (perfectly sharp:1.3), realistic textures, (deep focus:1.5), 8k uhd, dslr, ultra high quality image, film grain, Fujifilm XT3'
38
+ parameters:
39
+ negative_prompt: AliLarter_flux_lora_v5_Weight-1.00
40
+
41
+ output:
42
+ url: >-
43
+ 58122811.jpeg
44
+ - text: 'Breathtaking photography of ohwx woman with ultra narrow waist. A portrait of a young woman and her dog in a canoe on a calm lake. The woman wears a red life jacket with a logo, a gray shirt, and black leggings. The dog, with a white and tan coat, sits beside her, wearing a red collar with a black tag. The canoe is made of wood and has a wooden oar. The background shows a serene lake surrounded by trees with yellow leaves, indicating autumn. The sky is clear and blue, suggesting a sunny day. The image conveys a sense of serenity and companionship., emphasizing the woman''s form and the natural beauty of the beach. A candid photo shot of a young woman. (perfectly sharp:1.3), realistic textures, (deep focus:1.5), 8k uhd, dslr, ultra high quality image, film grain, Fujifilm XT3'
45
+ parameters:
46
+ negative_prompt: AliLarter_flux_lora_v5_Weight-1.10
47
+
48
+ output:
49
+ url: >-
50
+ 58122962.jpeg
51
+ - text: 'Breathtaking photography of ohwx woman with ultra narrow waist. A portrait of a young woman against a solid blue background. She wears a white karate uniform with black stripes on the sleeves and cuffs. Her long brown hair flows down her back. She is positioned in a side profile, her hands clasped together in front of her face. Her gaze is directly at the camera, and she has a neutral expression. The image style is professional and clean, emphasizing the subject''s facial features and clothing., emphasizing the woman''s form and the natural beauty of the beach. A candid photo shot of a young woman. (perfectly sharp:1.3), realistic textures, (deep focus:1.5), 8k uhd, dslr, ultra high quality image, film grain, Fujifilm XT3'
52
+ parameters:
53
+ negative_prompt: AliLarter_flux_lora_v5_Weight-1.00
54
+
55
+ output:
56
+ url: >-
57
+ 58122995.jpeg
58
+
59
+ ---
60
+
61
+ # πŸ‘‘ Ali Larter (Flux) 🎬
62
+
63
+ <Gallery />
64
+
65
+
66
+
67
+
68
+
69
+ ## Model description
70
+
71
+ <h1 id="***-if-you-love-it-like-it!-***-my25dnpnt">πŸ‘ <span style="color:rgb(64, 192, 87)">***</span> <strong><em><span style="color:rgb(34, 139, 230)">If you love it, like it!</span></em></strong> <span style="color:rgb(64, 192, 87)">***</span>πŸ‘</h1><p><em>workflow: </em><a target="_blank" rel="ugc" href="https://civitai.com/models/1088678"><em>https://civitai.com/models/1088678</em></a></p><h1 id="ali-larter-rr0ct61ia">πŸ‘‘ <span style="color:rgb(121, 80, 242)">Ali Larter </span>🎬</h1><p><strong>About my celebrities loras</strong><br />90% of the dataset used to build my loras only use head images. That really help the blend with other lora or model as there is no hands, feet, that may or will interfere in the final image render. When you get distorted hands with a person lora, it's because there is info on hands in the dataset used to train the lora, but that will not happen with my loras.</p><p>I've trained on Flux.1 Dev so other merged or trained checkpoint may not work well with my loras.</p><p>The drawback side of that is that the body may not be reflecting the reality. It may not be a drawback tho.</p><p></p><p>This is a lora for Flux.1 Dev. Work with other model but you must drop some simple bloc (good start 19-32).</p><p>Trained with ai-toolkit, so merging it is not easy.</p><p></p><p><strong>To get the best result</strong></p><p><em>Guidance: </em><strong><em>2.2-3</em></strong></p><p><em>Steps (dev): </em><strong><em>30-40</em></strong></p><p><em>daemon detailer (lying sigma sampler): factor: -0.02, start 0.06, end 0.75</em></p><p><em>Resolution: </em><strong><em>Upscale the latent by 1.25 or 1.5</em></strong><em> you'll get awsome result. (take longer time but worth it)</em></p><p><em>Trigger word is (may work better in certain context): </em><strong><em>ohwx</em></strong></p><p></p><p>Enjoy!</p>
72
+
73
+ ## Trigger words
74
+ You should use `ohwx` to trigger the image generation.
75
+
76
+
77
+ ## Download model
78
+
79
+ Weights for this model are available in Safetensors format.
80
+
81
+ [Download](/Keltezaa/ali-larter-flux/tree/main) them in the Files & versions tab.
82
+
83
+ ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
84
+
85
+ ```py
86
+ from diffusers import AutoPipelineForText2Image
87
+ import torch
88
+
89
+ device = "cuda" if torch.cuda.is_available() else "cpu"
90
+
91
+ pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
92
+ pipeline.load_lora_weights('Keltezaa/ali-larter-flux', weight_name='AliLarter_flux_lora_v5.safetensors')
93
+ image = pipeline('Breathtaking photography of ohwx woman with ultra narrow waist. A portrait of a young woman against a solid blue background. She wears a white karate uniform with black stripes on the sleeves and cuffs. Her long brown hair flows down her back. She is positioned in a side profile, her hands clasped together in front of her face. Her gaze is directly at the camera, and she has a neutral expression. The image style is professional and clean, emphasizing the subject's facial features and clothing., emphasizing the woman's form and the natural beauty of the beach. A candid photo shot of a young woman. (perfectly sharp:1.3), realistic textures, (deep focus:1.5), 8k uhd, dslr, ultra high quality image, film grain, Fujifilm XT3').images[0]
94
+ ```
95
+
96
+ 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)
97
+