lrzjason commited on
Commit
af330b7
·
verified ·
1 Parent(s): 4bf408a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +62 -3
README.md CHANGED
@@ -1,3 +1,62 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model:
4
+ - Qwen/Qwen-Image-Edit-2511
5
+ library_name: diffusers
6
+ tags:
7
+ - lora
8
+ pipeline_tag: image-to-image
9
+ ---
10
+ ## [RELEASE] New Version of Anything2Real LoRA - Transform Any Art Style to Photorealistic Images Based On Qwen Edit 2511
11
+
12
+ Hey Stable Diffusion community! 👋
13
+
14
+ I'm excited to share the new version of - **Anything2Real**, a specialized LoRA built on the powerful Qwen Edit 2509 (mmdit editing model) that transforms ANY art style into photorealistic images!
15
+
16
+ Demo Alpha Dataset: [lrzjason/Anything2Real_demo_dataset](https://huggingface.co/datasets/lrzjason/Anything2Real_demo_dataset)
17
+
18
+ **🔗 Civitai:** https://civitai.com/models/2121900/qwen-edit-2511-anything2real-2601
19
+
20
+ ## 🎯 What It Does
21
+ This LoRA is designed to convert illustrations, anime, cartoons, paintings, and other non-photorealistic images into convincing photographs while preserving the original composition and content.
22
+
23
+ ## ⚙️ How to Use
24
+ - **Base Model:** Qwen Edit 2511 (mmdit editing model)
25
+ - **Recommended Strength:** 1-0.75
26
+ - **Prompt Template:**
27
+ ```
28
+ change the picture 1 to realistic photograph, [description of your image]
29
+ ```
30
+ - Adding detailed descriptions helps the model better understand content and produces superior transformations (though it works even without detailed prompts!)
31
+
32
+ ## 📺 Example Workflow
33
+ Check out this practical implementation example on RunningHub:
34
+ https://www.runninghub.ai/post/1988649905554112513/?inviteCode=rh-v1279
35
+
36
+ **Node Information:**
37
+ - 21 nodes including CLIPLoader, ConditioningZeroOut, ImageScaleBy, KSampler, LoadImage, LoraLoaderModelOnly, and specialized Qwen Edit nodes
38
+ - Powered by RTX 4090 Series
39
+
40
+ ## 📌 Important Notes
41
+ - This is an **alpha version** still in active development
42
+ - Current release was trained on a limited dataset
43
+ - The ultimate goal is to create a robust, generalized solution for style-to-photo conversion
44
+ - Your feedback and examples would be incredibly valuable for future improvements!
45
+
46
+ ## 💡 Why I Created This
47
+ I wanted to bridge the gap between artistic creations and photorealistic results without having to start from scratch. Whether you're an artist wanting to see your characters in realistic form, or just curious about transforming your favorite art styles into photographs, this tool is for you!
48
+
49
+ I'd love to see what you create with Anything2Real! Please share your results and suggestions in the comments. Every test case helps improve the next version.
50
+
51
+ ---
52
+
53
+ *Note: For best results, follow the workflow demonstrated in the RunningHub example. Feel free to reach out with questions or collaboration ideas!*
54
+
55
+
56
+ ## Contact
57
+ Feel free to reach out via any of the following channels:
58
+ Twitter: @Lrzjason
59
+ Email: lrzjason@gmail.com
60
+ QQ Group: 866612947
61
+ WeChat ID: fkdeai
62
+ CivitAI: xiaozhijason