bobrity commited on
Commit
7953182
·
verified ·
1 Parent(s): 9437c48

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +79 -0
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: openrail++
3
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
4
+ tags:
5
+ - stable-diffusion-xl
6
+ - stable-diffusion
7
+ - text-to-image
8
+ - diffusers
9
+ - safetensors
10
+ inference: true
11
+ ---
12
+
13
+ # AnalogMadness SDXL XL3
14
+
15
+ AnalogMadness SDXL XL3 is a fine-tuned Stable Diffusion XL model that specializes in creating analog photography-style images with enhanced artistic quality and distinctive visual characteristics.
16
+
17
+ ## Model Details
18
+
19
+ - **Base Model**: stabilityai/stable-diffusion-xl-base-1.0
20
+ - **Model Type**: Stable Diffusion XL fine-tuned checkpoint
21
+ - **File Format**: SafeTensors
22
+ - **File Size**: ~6.5GB
23
+ - **Resolution**: 1024x1024 (native SDXL resolution)
24
+
25
+ ## Intended Use
26
+
27
+ This model is intended for:
28
+ - Creating analog photography-style artwork
29
+ - Generating images with vintage aesthetic
30
+ - Artistic and creative image generation
31
+ - Research and experimentation with diffusion models
32
+
33
+ ## Usage
34
+
35
+ ### Using with Diffusers
36
+
37
+ ```python
38
+ from diffusers import DiffusionPipeline
39
+ import torch
40
+
41
+ pipeline = DiffusionPipeline.from_pretrained(
42
+ "your-username/analogmadness-sdxl",
43
+ torch_dtype=torch.float16,
44
+ use_safetensors=True
45
+ )
46
+ pipeline = pipeline.to("cuda")
47
+
48
+ prompt = "analog photography of a sunset over the ocean, vintage film grain"
49
+ image = pipeline(prompt).images[0]
50
+ image.save("analog_sunset.png")
51
+ ```
52
+
53
+ ### Using with ComfyUI
54
+
55
+ 1. Download the `model.safetensors` file
56
+ 2. Place it in your ComfyUI `models/checkpoints/` directory
57
+ 3. Refresh ComfyUI and select the model from the checkpoint loader
58
+
59
+ ## Recommended Settings
60
+
61
+ - **Sampling Steps**: 20-30
62
+ - **Guidance Scale**: 7-12
63
+ - **Negative Prompt**: "digital art, cgi, 3d render, cartoon"
64
+ - **Scheduler**: DPM++ 2M Karras or Euler A
65
+
66
+ ## Sample Prompts
67
+
68
+ - "analog photography of a vintage car, film grain, warm tones"
69
+ - "portrait of a woman, analog film style, soft lighting"
70
+ - "street photography, 35mm film, urban landscape"
71
+ - "vintage nature scene, analog camera, golden hour"
72
+
73
+ ## License
74
+
75
+ This model is released under the OpenRAIL++ license. Please ensure compliance with the license terms when using this model.
76
+
77
+ ## Disclaimer
78
+
79
+ This model should be used responsibly and in accordance with ethical AI practices. The creators are not responsible for any misuse of this technology.