Hugging Face's logo

Spaces:
Onise
/
anycoder-5f028fd4
Runtime error

App Files Community
Onise commited on
Commit
65c5b13
·
verified ·
1 Parent(s): e009c22

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +182 -3
README.md CHANGED
@@ -1,14 +1,193 @@
1
  ---
2
  title: Anycoder 5f028fd4
3
  emoji: 🏢
4
- colorFrom: blue
5
  colorTo: blue
6
  sdk: gradio
7
- sdk_version: 6.0.2
8
  app_file: app.py
9
  pinned: false
10
  tags:
11
  - anycoder
12
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
 
14
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
1
  ---
2
  title: Anycoder 5f028fd4
3
  emoji: 🏢
4
+ colorFrom: indigo
5
  colorTo: blue
6
  sdk: gradio
7
+ sdk_version: 6.6.0
8
  app_file: app.py
9
  pinned: false
10
  tags:
11
  - anycoder
12
  ---
13
+ === README.md ===
14
+ ```markdown
15
+ ---
16
+ title: 🎨 Magic Wan Image V2 - Text to Image
17
+ emoji: 🎨
18
+ colorFrom: indigo
19
+ colorTo: purple
20
+ sdk: gradio
21
+ sdk_version: 6.0.2
22
+ app_file: app.py
23
+ pinned: false
24
+ license: apache-2.0
25
+ tags:
26
+ - text-to-image
27
+ - diffusers
28
+ - wan
29
+ - lora
30
+ - image-generation
31
+ - ai-art
32
+ - gradio
33
+ ---
34
+
35
+ # 🎨 Magic Wan Image V2 - Text to Image Generator
36
+
37
+ Generate stunning images from text prompts with **Real Wan LoRA Support**! This Space uses the [Magic-Wan-Image-V2](https://huggingface.co/wikeeyang/Magic-Wan-Image-V2) model with support for various Wan-compatible LoRA adapters.
38
+
39
+ <div align="center">
40
+ <a href="https://huggingface.co/spaces/akhaliq/anycoder">
41
+ <img src="https://img.shields.io/badge/Built%20with-anycoder-FF9D00?style=for-the-badge" alt="Built with anycoder">
42
+ </a>
43
+ </div>
44
+
45
+ ## ✨ Features
46
+
47
+ - **🎭 Multiple LoRA Styles**: Choose from 15+ Wan-compatible LoRA adapters including:
48
+ - Anime/Manga Style
49
+ - Realistic Vision
50
+ - Oil Painting
51
+ - Watercolor
52
+ - Pixel Art
53
+ - 3D Render
54
+ - Sketch
55
+ - Cyberpunk
56
+ - Fantasy
57
+ - Studio Ghibli
58
+ - Vintage Photo
59
+ - Pop Art
60
+ - Minimalist
61
+ - Horror
62
+ - Concept Art
63
+
64
+ - **⚙️ Full Control**: Adjust all generation parameters:
65
+ - Width & Height (256-1024px)
66
+ - Inference Steps (10-100)
67
+ - Guidance Scale (1.0-20.0)
68
+ - Seed (with randomization option)
69
+ - LoRA Scale (0.0-2.0)
70
+
71
+ - **📚 Example Prompts**: Click pre-made examples to quickly test different styles
72
+
73
+ - **🚀 Optimized Performance**: FP16 inference with CUDA acceleration when available
74
+
75
+ ## 🚀 How to Use
76
+
77
+ 1. **Enter your prompt**: Describe the image you want to generate in the Prompt box
78
+ 2. **Optional negative prompt**: Specify what to avoid in the generated image
79
+ 3. **Select a LoRA style**: Choose from the dropdown menu (or keep "None" for base model)
80
+ 4. **Adjust settings**: Modify LoRA scale, dimensions, steps, and guidance as needed
81
+ 5. **Click Generate**: Wait for your image to be generated!
82
+
83
+ ### 💡 Tips for Better Results
84
+
85
+ | Parameter | Recommendation |
86
+ |-----------|----------------|
87
+ | **Prompt** | Be descriptive and specific. Include style, lighting, composition details |
88
+ | **LoRA Scale** | Start at 1.0, increase for stronger style effect (max 2.0) |
89
+ | **Steps** | 30 steps is a good balance. More steps = better quality but slower |
90
+ | **Guidance** | 7.5 is default. Higher = more prompt adherence, lower = more creative |
91
+ | **Seed** | Use same seed for reproducible results, or randomize for variety |
92
+
93
+ ### 📝 Example Prompts
94
+
95
+ ```
96
+ A cyberpunk city at night, neon lights, rain, highly detailed, 8k
97
+ Portrait of a fantasy elf warrior, intricate armor, forest background
98
+ Magical library with floating books, mystical atmosphere, warm lighting
99
+ Steampunk airship flying through clouds, detailed mechanical parts
100
+ ```
101
+
102
+ ## 🏗️ Technical Details
103
+
104
+ ### Model Information
105
+
106
+ - **Base Model**: [Magic-Wan-Image-V2](https://huggingface.co/wikeeyang/Magic-Wan-Image-V2)
107
+ - **Framework**: Diffusers + PyTorch
108
+ - **Precision**: FP16 (for faster inference)
109
+ - **LoRA Support**: Full Wan-compatible LoRA adapter support
110
+
111
+ ### LoRA Adapters
112
+
113
+ All LoRA adapters are automatically downloaded from Hugging Face Hub on first use and cached locally. The following repositories are used:
114
+
115
+ | LoRA Name | Repository |
116
+ |-----------|------------|
117
+ | Anime Style | AlienKevin/Wan2.1-LoRA-Anime |
118
+ | Realistic Vision | prithivMLmods/Wan-Realistic-LoRA |
119
+ | Oil Painting | strangerzonehf/Wan2.1-LoRA-Oil-Painting |
120
+ | Watercolor | strangerzonehf/Wan2.1-LoRA-Watercolor |
121
+ | Pixel Art | strangerzonehf/Wan2.1-LoRA-Pixel-Art |
122
+ | 3D Render | prithivMLmods/Wan-3D-Render-LoRA |
123
+ | Sketch | strangerzonehf/Wan2.1-LoRA-Sketch |
124
+ | Cyberpunk | prithivMLmods/Wan-Cyberpunk-LoRA |
125
+ | Fantasy | prithivMLmods/Wan-Fantasy-LoRA |
126
+ | Studio Ghibli | AlienKevin/Wan2.1-LoRA-Ghibli |
127
+ | Vintage Photo | strangerzonehf/Wan2.1-LoRA-Vintage |
128
+ | Pop Art | strangerzonehf/Wan2.1-LoRA-Pop-Art |
129
+ | Minimalist | prithivMLmods/Wan-Minimalist-LoRA |
130
+ | Horror | prithivMLmods/Wan-Horror-LoRA |
131
+ | Concept Art | prithivMLmods/Wan-Concept-Art-LoRA |
132
+
133
+ ### Hardware Requirements
134
+
135
+ - **Minimum**: CPU (slower generation)
136
+ - **Recommended**: GPU with 8GB+ VRAM for fast generation
137
+ - **Optimal**: GPU with 12GB+ VRAM for larger resolutions
138
+
139
+ ## 📦 Installation (Local)
140
+
141
+ To run this Space locally:
142
+
143
+ ```bash
144
+ # Clone the repository
145
+ git clone https://huggingface.co/spaces/YOUR_USERNAME/magic-wan-image-v2
146
+ cd magic-wan-image-v2
147
+
148
+ # Install dependencies
149
+ pip install -r requirements.txt
150
+
151
+ # Run the app
152
+ python app.py
153
+ ```
154
+
155
+ ## 🔗 Links & Resources
156
+
157
+ - **Base Model**: [Magic-Wan-Image-V2](https://huggingface.co/wikeeyang/Magic-Wan-Image-V2)
158
+ - **Diffusers Documentation**: [Hugging Face Diffusers](https://huggingface.co/docs/diffusers)
159
+ - **Gradio Documentation**: [Gradio 6 Docs](https://gradio.app/docs)
160
+ - **Built with**: [anyCoder](https://huggingface.co/spaces/akhaliq/anycoder)
161
+
162
+ ## 📄 License
163
+
164
+ This Space is licensed under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0).
165
+
166
+ Please check the individual LoRA model licenses for their specific terms.
167
+
168
+ ## 🙏 Credits
169
+
170
+ - **Base Model**: [@wikeeyang](https://huggingface.co/wikeeyang) for Magic-Wan-Image-V2
171
+ - **LoRA Creators**: Various creators on Hugging Face Hub
172
+ - **Framework**: [Gradio](https://gradio.app) team
173
+ - **Built with**: [anyCoder](https://huggingface.co/spaces/akhaliq/anycoder)
174
+
175
+ ## 🐛 Issues & Support
176
+
177
+ If you encounter any issues:
178
+
179
+ 1. Check the console logs for error messages
180
+ 2. Try reducing image resolution
181
+ 3. Ensure your prompt is not empty
182
+ 4. Report issues on the Space discussion tab
183
+
184
+ ---
185
+
186
+ <div align="center">
187
+
188
+ **Made with ❤️ using Gradio 6**
189
+
190
+ [Built with anycoder](https://huggingface.co/spaces/akhaliq/anycoder) | [Report Issue](https://huggingface.co/spaces/YOUR_USERNAME/magic-wan-image-v2/discussions)
191
 
192
+ </div>
193
+ ```