Downloads · 30 days
9
0% of all-time downloads
kandinsky3_ip_adapter
ai-forever/kandinsky3_ip_adapter
kandinsky3_ip_adapter is a text-to-image model from ai-forever. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
All-time downloads
4.9K
Public
Repo size
52.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin50.9 GB · 98%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Access
- Public
- Created
- Apr 3, 2024
- Updated
- Apr 4, 2024
- SHA
- 1c703eab
Model card
From the Hugging Face model README
Kandinsky 3.0 IP Adapter
Usage
pip install git+https://github.com/ai-forever/kandinsky3-diffusers.git
Image variations
from diffusers.models.attention_processor import Kandi3AttnProcessorIpAdapter, Kandi3AttnProcessor
from diffusers.pipelines.kandinsky3.kandinsky3_pipeline_ip_adapter import KandinskyV3PipelineIpAdapter
from PIL import Image
import torch
pipe = KandinskyV3PipelineIpAdapter.from_pretrained('ai-forever/kandinsky3_ip_adapter', torch_dtype=torch.float16, low_cpu_mem_usage=False, device_map=None)
pipe = pipe.to('cuda')
img = Image.open('path_to_img.jpg')
out_img = pipe('4k caption', img=[img], weights=[1], negative_prompt='', height=1024, width=1024, guidance_scale=7.5, num_inference_steps=50, cut_context=1)[0][0]
Image + Image mixing
from diffusers.models.attention_processor import Kandi3AttnProcessorIpAdapter, Kandi3AttnProcessor
from diffusers.pipelines.kandinsky3.kandinsky3_pipeline_ip_adapter import KandinskyV3PipelineIpAdapter
from PIL import Image
import torch
pipe = KandinskyV3PipelineIpAdapter.from_pretrained('ai-forever/kandinsky3_ip_adapter', torch_dtype=torch.float16, low_cpu_mem_usage=False, device_map=None)
pipe = pipe.to('cuda')
img1 = Image.open('path_to_img1.jpg')
img2 = Image.open('path_to_img2.jpg')
out_img = pipe('4k photo', img=[img1, img2], weights=[0.5, 0.5], negative_prompt='', height=1024, width=1024, guidance_scale=7.5, num_inference_steps=50, cut_context=1)[0][0]
Text + Image mixing
from diffusers.models.attention_processor import Kandi3AttnProcessorIpAdapter, Kandi3AttnProcessor
from diffusers.pipelines.kandinsky3.kandinsky3_pipeline_ip_adapter import KandinskyV3PipelineIpAdapter
from PIL import Image
import torch
pipe = KandinskyV3PipelineIpAdapter.from_pretrained('ai-forever/kandinsky3_ip_adapter', torch_dtype=torch.float16, low_cpu_mem_usage=False, device_map=None)
pipe = pipe.to('cuda')
img = Image.open('path_to_img.jpg')
caption = 'cat, 4k photo'
out_img = pipe(caption, img=[img], weights=[1], negative_prompt='', height=1024, width=1024, guidance_scale=7.5, num_inference_steps=50, cut_context=1, img_weight=0.5)[0][0]
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Created
- Apr 3, 2024
- Updated
- Apr 4, 2024