Flourish commited on
Commit
daf1cb2
ยท
verified ยท
1 Parent(s): d9d3eb1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -5
README.md CHANGED
@@ -58,8 +58,30 @@ Here are some examples demonstrating the capabilities of Ovis-Image.
58
  </figure>
59
 
60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
- ## ๐Ÿ“ฆ Installation
 
 
 
 
 
 
 
63
 
64
  Ovis-Image has been tested with Python 3.10, Torch 2.6.0, and Transformers 4.57.1. For a full list of package dependencies, please see `requirements.txt`.
65
 
@@ -72,9 +94,8 @@ pip install -r requirements.txt
72
  pip install -e .
73
  ```
74
 
75
- ## ๐Ÿ› ๏ธ Inference
76
-
77
  For text-to-image, please run
 
78
  ```bash
79
  python ovis_image/test.py \
80
  --model_path AIDC-AI/Ovis-Image-7B/ovis_image.safetensors \
@@ -84,13 +105,12 @@ python ovis_image/test.py \
84
  --denoising_steps 50 \
85
  --cfg_scale 5.0 \
86
  --prompt "A creative 3D artistic render where the text \"OVIS-IMAGE\" is written in a bold, expressive handwritten brush style using thick, wet oil paint. The paint is a mix of vibrant rainbow colors (red, blue, yellow) swirling together like toothpaste or impasto art. You can see the ridges of the brush bristles and the glossy, wet texture of the paint. The background is a clean artist's canvas. Dynamic lighting creates soft shadows behind the floating paint strokes. Colorful, expressive, tactile texture, 4k detail." \
87
-
88
  ```
89
 
90
-
91
  Alternatively, you can try Ovis-Image directly in your browser on [![Hugging Face Space](https://img.shields.io/badge/๐ŸŽจ_HF_Spaces-AIDC--AI/Ovis--Image--7B-lightblack)](https://huggingface.co/spaces/AIDC-AI/Ovis-Image-7B)
92
 
93
 
 
94
  ## ๐Ÿ“Š Performance
95
 
96
 
 
58
  </figure>
59
 
60
 
61
+ ## ๐Ÿ› ๏ธ Inference
62
+
63
+ ### Inference with Diffusers
64
+
65
+ First, install the `diffusers` library with support for Ovis-Image.
66
+
67
+ ```bash
68
+ pip install git+https://github.com/DoctorKey/diffusers.git@ovis-image
69
+ ```
70
+
71
+ Next, use the `OvisImagePipeline` to generate the image.
72
+
73
+ ```python
74
+ import torch
75
+ from diffusers import OvisImagePipeline
76
 
77
+ pipe = OvisImagePipeline.from_pretrained("AIDC-AI/Ovis-Image-7B", torch_dtype=torch.bfloat16)
78
+ pipe.to("cuda")
79
+ prompt = "A creative 3D artistic render where the text \"OVIS-IMAGE\" is written in a bold, expressive handwritten brush style using thick, wet oil paint. The paint is a mix of vibrant rainbow colors (red, blue, yellow) swirling together like toothpaste or impasto art. You can see the ridges of the brush bristles and the glossy, wet texture of the paint. The background is a clean artist's canvas. Dynamic lighting creates soft shadows behind the floating paint strokes. Colorful, expressive, tactile texture, 4k detail."
80
+ image = pipe(prompt, negative_prompt="", num_inference_steps=50, true_cfg_scale=5.0).images[0]
81
+ image.save("ovis_image.png")
82
+ ```
83
+
84
+ ### Inference with Pytorch
85
 
86
  Ovis-Image has been tested with Python 3.10, Torch 2.6.0, and Transformers 4.57.1. For a full list of package dependencies, please see `requirements.txt`.
87
 
 
94
  pip install -e .
95
  ```
96
 
 
 
97
  For text-to-image, please run
98
+
99
  ```bash
100
  python ovis_image/test.py \
101
  --model_path AIDC-AI/Ovis-Image-7B/ovis_image.safetensors \
 
105
  --denoising_steps 50 \
106
  --cfg_scale 5.0 \
107
  --prompt "A creative 3D artistic render where the text \"OVIS-IMAGE\" is written in a bold, expressive handwritten brush style using thick, wet oil paint. The paint is a mix of vibrant rainbow colors (red, blue, yellow) swirling together like toothpaste or impasto art. You can see the ridges of the brush bristles and the glossy, wet texture of the paint. The background is a clean artist's canvas. Dynamic lighting creates soft shadows behind the floating paint strokes. Colorful, expressive, tactile texture, 4k detail." \
 
108
  ```
109
 
 
110
  Alternatively, you can try Ovis-Image directly in your browser on [![Hugging Face Space](https://img.shields.io/badge/๐ŸŽจ_HF_Spaces-AIDC--AI/Ovis--Image--7B-lightblack)](https://huggingface.co/spaces/AIDC-AI/Ovis-Image-7B)
111
 
112
 
113
+
114
  ## ๐Ÿ“Š Performance
115
 
116