Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,9 @@ pipeline_tag: image-to-image
|
|
| 12 |
This repository contains the **FP8 quantized version** of the Qwen-Image-Edit-2511 model.
|
| 13 |
It is designed for efficient inference while maintaining high-quality image editing capabilities.
|
| 14 |
|
|
|
|
|
|
|
|
|
|
| 15 |
---
|
| 16 |
|
| 17 |
## 🔑 Features
|
|
@@ -22,6 +25,60 @@ It is designed for efficient inference while maintaining high-quality image edit
|
|
| 22 |
|
| 23 |
---
|
| 24 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
## 🚀 Quick Start
|
| 26 |
|
| 27 |
### 1. Install Dependencies
|
|
|
|
| 12 |
This repository contains the **FP8 quantized version** of the Qwen-Image-Edit-2511 model.
|
| 13 |
It is designed for efficient inference while maintaining high-quality image editing capabilities.
|
| 14 |
|
| 15 |
+
<p align="center">
|
| 16 |
+
<img src="https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen-Image/edit2511/edit2511big.JPG#center" width="1600"/>
|
| 17 |
+
<p>
|
| 18 |
---
|
| 19 |
|
| 20 |
## 🔑 Features
|
|
|
|
| 25 |
|
| 26 |
---
|
| 27 |
|
| 28 |
+
## Showcase
|
| 29 |
+
|
| 30 |
+
**Qwen-Image-Edit-2511 Enhances Character Consistency**
|
| 31 |
+
In Qwen-Image-Edit-2511, character consistency has been significantly improved. The model can perform imaginative edits based on an input portrait while preserving the identity and visual characteristics of the subject.
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
**Improved Multi-Person Consistency**
|
| 39 |
+
While Qwen-Image-Edit-2509 already improved consistency for single-subject editing, Qwen-Image-Edit-2511 further enhances consistency in multi-person group photos—enabling high-fidelity fusion of two separate person images into a coherent group shot:
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
**Built-in Support for Community-Created LoRAs**
|
| 44 |
+
Since Qwen-Image-Edit’s release, the community has developed many creative and high-quality LoRAs—greatly expanding its expressive potential. Qwen-Image-Edit-2511 integrates selected popular LoRAs directly into the base model, unlocking their effects without extra tuning.
|
| 45 |
+
|
| 46 |
+
For example, Lighting Enhancement LoRA
|
| 47 |
+
Realistic lighting control is now achievable out-of-the-box:
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
Another example, generating new viewpoints can now be done directly with the base model:
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
**Industrial Design Applications**
|
| 59 |
+
|
| 60 |
+
We’ve paid special attention to practical engineering scenarios—for instance, batch industrial product design:
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
…and material replacement for industrial components:
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
**Enhanced Geometric Reasoning**
|
| 73 |
+
Qwen-Image-Edit-2511 introduces stronger geometric reasoning capability—e.g., directly generating auxiliary construction lines for design or annotation purposes:
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
---
|
| 81 |
+
|
| 82 |
## 🚀 Quick Start
|
| 83 |
|
| 84 |
### 1. Install Dependencies
|