T2I-Adapter: A Python repository from haofanwang

⏬Download Models | 💻How to Test | 💥

T2I adapters naturally support using multiple adapters together.
The running command is here
Image source

🚩 New Features/Updates

✅ Feb. 23, 2023. Add the depth adapter t2iadapter_depth_sd14v1.pth. See more info in the Adapter Zoo.

Official implementation of T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models.

We propose T2I-Adapter, a simple and small (~70M parameters, ~300M storage space) network that can provide extra guidance to pre-trained text-to-image models while freezing the original large text-to-image models.

T2I-Adapter aligns internal knowledge in T2I models with external control signals. We can train various adapters according to different conditions, and achieve rich control and editing effects.

⏬ Download Models

Put the downloaded models in the T2I-Adapter/models folder.

The T2I-Adapters can be download from https://huggingface.co/TencentARC/T2I-Adapter.
The pretrained Stable Diffusion v1.4 models can be download from https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/tree/main. You need to download the sd-v1-4.ckpt file.
[Optional] If you want to use Anything v4.0 models, you can download the pretrained models from https://huggingface.co/andite/anything-v4.0/tree/main. You need to download the anything-v4.0-pruned.ckpt file.
The pretrained clip-vit-large-patch14 folder can be download from https://huggingface.co/openai/clip-vit-large-patch14/tree/main. Remember to download the whole folder!
The pretrained keypose detection models include FasterRCNN (human detection) from https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth and HRNet (pose detection) from https://download.openmmlab.com/mmpose/top_down/hrnet/hrnet_w48_coco_256x192-b9e0b3ab_20200708.pth.

After downloading, the folder structure should be like this:

🔧 Dependencies and Installation

Python >= 3.6 (Recommend to use Anaconda or Miniconda)
PyTorch >= 1.4

pip install -r requirements.txt

If you want to use the full function of keypose-guided generation, you need to install MMPose. For details please refer to https://github.com/open-mmlab/mmpose.

💻 How to Test

Depth Adapter

python test_depth.py --prompt "Stormtrooper's lecture, best quality, extremely detailed" --path_cond examples/depth/sd.png --ckpt models/v1-5-pruned-emaonly.ckpt --type_in image --sampler ddim --scale 9 --cond_weight 1.5

Sketch Adapter

Sketch to Image Generation

python test_sketch.py --prompt "A car with flying wings" --path_cond examples/sketch/car.png --ckpt models/sd-v1-4.ckpt --type_in sketch

Image to Sketch to Image Generation

python test_sketch.py --prompt "A beautiful girl" --path_cond examples/sketch/human.png --ckpt models/sd-v1-4.ckpt --type_in image

The adaptor is training based on stable-diffusion-v1.4 but can be generalized to other models, such as Anything-v4 which is an anime diffusion model

python test_sketch.py --prompt "1girl, masterpiece, high-quality, high-res" --path_cond examples/anything_sketch/human.png --ckpt models/anything-v4.0-pruned.ckpt --ckpt_vae models/anything-v4.0.vae.pt --type_in image

Keypose Adapter

Keypose to Image Generation

python test_keypose.py --prompt "A beautiful girl" --path_cond examples/keypose/iron.png --type_in pose

Image to Image Generation

python test_keypose.py --prompt "A beautiful girl" --path_cond examples/sketch/human.png --type_in image

Generation anime image with Anything-v4 model

python test_keypose.py --prompt "A beautiful girl" --path_cond examples/sketch/human.png --ckpt models/anything-v4.0-pruned.ckpt --ckpt_vae models/anything-v4.0.vae.pt --type_in image

Segmentation Adapter

python test_seg.py --prompt "A black Honda motorcycle parked in front of a garage" --path_cond examples/seg/motor.png

Combine multiple Adapters

python test_composable_adapters.py --prompt "An all white kitchen with an electric stovetop" --seg_cond_path examples/seg_sketch/mask.png --sketch_cond_path examples/seg_sketch/edge.png --sketch_cond_weight 0.5

Local editing with adapters

python test_sketch_edit.py --prompt "A white cat" --path_cond examples/edit_cat/edge_2.png --path_x0 examples/edit_cat/im.png --path_mask examples/edit_cat/mask.png

Stable Diffusion + T2I-Adapters (only ~70M parameters, ~300M storage space)

The following is the detailed structure of a Stable Diffusion model with the T2I-Adapter.

🚀 Interesting Applications

Stable Diffusion results guided with the sketch T2I-Adapter

The corresponding edge maps are predicted by PiDiNet. The sketch T2I-Adapter can well generalize to other similar sketch types, for example, sketches from the Internet and user scribbles.

Stable Diffusion results guided with the keypose T2I-Adapter

The keypose results predicted by the MMPose. With the keypose guidance, the keypose T2I-Adapter can also help to generate animals with the same keypose, for example, pandas and tigers.

T2I-Adapter with Anything-v4.0

Once the T2I-Adapter is trained, it can act as a plug-and-play module and can be seamlessly integrated into the finetuned diffusion models without re-training, for example, Anything-4.0.