Hugging Face's logo

Kr1sJ
/
iMontage

Image-to-Image
Diffusers
Safetensors
Model card Files
xet
Community
1
Kr1sJ commited on
Commit
ce35ca9
·
verified ·
1 Parent(s): 782ea8d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -11,7 +11,7 @@ library_name: diffusers
11
  [![GitHub](https://img.shields.io/badge/GitHub-Code-keygen.svg?logo=github&style=flat-square)](https://github.com/Kr1sJFU/iMontage)
12
 
13
  <p align="center">
14
- <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/demo/teaser.png" alt="iMontage Teaser" width="85%">
15
  </p>
16
 
17
  iMontage is a unified framework designed to repurpose a powerful video model into an all-in-one image generator. The framework consumes and produces variable-length image sets, unifying a wide array of image generation and editing tasks. This approach allows the model to acquire broad image manipulation capabilities without corrupting its invaluable original motion priors. iMontage excels across several mainstream many-in-many-out tasks, maintaining strong cross-image contextual consistency and generating scenes with extraordinary dynamics.
@@ -64,12 +64,12 @@ The model supports various tasks as illustrated below:
64
 
65
  | **Task Type** | **Input** | **Prompt** | **Output** |
66
  |----------------------|-------------------------------------------------------------|----------------------------------------------------------------|-------------------------------------------------------------|
67
- | **image_editing** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/llava.png" width="120"> | *Change the material of the lava to silver.* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/results/llava_0.png" width="120"> |
68
- | **cref** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/Confucius.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/Moses.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/Solon.png" width="80"> | *Confucius from the first image, Moses from the second…* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/results/Confucius_0.png" width="120"> |
69
- | **conditioned_cref** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/depth.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/girl.png" width="80"> | *depth* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/results/depth_0.png" width="120"> |
70
- | **sref** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/woman.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/joker.png" width="80"> | *(empty)* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/results/woman_0.png" width="120"> |
71
- | **multiview** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/city.png" width="120"> | *1. Shift left; 2. Look up; 3. Zoom out.* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/results/city_0.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/results/city_1.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/results/city_2.png" width="80"> |
72
- | **storyboard** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/Hepburn.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/images/yellow_bag.png" width="80"> | *Vintage film: 1. Hepburn carrying the yellow bag…* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/results/Hepburn_0.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/results/Hepburn_1.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/assets/results/Hepburn_2.png" width="80"> |
73
 
74
  ## 💖 Acknowledgment
75
 
 
11
  [![GitHub](https://img.shields.io/badge/GitHub-Code-keygen.svg?logo=github&style=flat-square)](https://github.com/Kr1sJFU/iMontage)
12
 
13
  <p align="center">
14
+ <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/demo/teaser.png" alt="iMontage Teaser" width="85%">
15
  </p>
16
 
17
  iMontage is a unified framework designed to repurpose a powerful video model into an all-in-one image generator. The framework consumes and produces variable-length image sets, unifying a wide array of image generation and editing tasks. This approach allows the model to acquire broad image manipulation capabilities without corrupting its invaluable original motion priors. iMontage excels across several mainstream many-in-many-out tasks, maintaining strong cross-image contextual consistency and generating scenes with extraordinary dynamics.
 
64
 
65
  | **Task Type** | **Input** | **Prompt** | **Output** |
66
  |----------------------|-------------------------------------------------------------|----------------------------------------------------------------|-------------------------------------------------------------|
67
+ | **image_editing** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/llava.png" width="120"> | *Change the material of the lava to silver.* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/results/llava_0.png" width="120"> |
68
+ | **cref** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/Confucius.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/Moses.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/Solon.png" width="80"> | *Confucius from the first image, Moses from the second…* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/results/Confucius_0.png" width="120"> |
69
+ | **conditioned_cref** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/depth.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/girl.png" width="80"> | *depth* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/results/depth_0.png" width="120"> |
70
+ | **sref** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/woman.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/joker.png" width="80"> | *(empty)* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/results/woman_0.png" width="120"> |
71
+ | **multiview** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/city.png" width="120"> | *1. Shift left; 2. Look up; 3. Zoom out.* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/results/city_0.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/results/city_1.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/results/city_2.png" width="80"> |
72
+ | **storyboard** | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/Hepburn.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/images/yellow_bag.png" width="80"> | *Vintage film: 1. Hepburn carrying the yellow bag…* | <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/results/Hepburn_0.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/results/Hepburn_1.png" width="80"> <img src="https://huggingface.co/Kr1sJ/iMontage/resolve/main/results/Hepburn_2.png" width="80"> |
73
 
74
  ## 💖 Acknowledgment
75