Sponsored by
Vmake Labs Video Enhancer
-Vmake Labs Video Enhancer uses AI to improve video quality, restore details, reduce blur, and upscale videos to 8K.
This is a Distill LoRA for Z-Image that distills both steps and CFG. This model does not require CFG and uses 8 steps for inference.
Model Features
This is a Distill LoRA for Z-Image that distills both steps and CFG. It does not use any Z-Image-Turbo related weights and is trained from scratch. It is compatible with other Z-Image LoRAs and
Controls
.
This model will slightly reduce the output quality and change the output composition of the model. For specific comparisons, please refer to the Results section. In most cases, the Distill LoRA performs well; currently, the biggest issue is that it may make the generated results brighter.
The purpose of this model is to provide fast generation compatibility for Z-Image derivative models, not to replace Z-Image-Turbo.
TODO
Optimize the output brightness;
Train a 4-step LoRA.
Results
Work itself
Output 25 steps
Output 8 steps
Output 25 steps
Output 8 steps
Output 25 steps
Output 8 steps
Output 25 steps
Output 8 steps
Work with Controlnet
Pose + Inpaint
Output 25 steps
Output 8 steps
Pose + Inpaint
Output 25 steps
Output 8 steps
Pose
Output 25 steps
Output 8 steps
Pose
Output 25 steps
Output 8 steps
Canny
Output
Output 8 steps
Depth
Output
Output 8 steps
Inference
Go to the VideoX-Fun repository for more details.
Please clone the VideoX-Fun repository and create the required directories:
# Clone the code
git clone https://github.com/aigc-apps/VideoX-Fun.git
# Enter VideoX-Fun's directorycd VideoX-Fun
# Create model directoriesmkdir -p models/Diffusion_Transformer
mkdir -p models/Personalized_Model
Then download the weights into models/Diffusion_Transformer and models/Personalized_Model.
Set the lora_path="Personalized_Model/Z-Image-Fun-Lora-Distill-8-Steps.safetensors" in
examples/z_image_fun/predict_t2i_control_2.1.py
and
examples/z_image_fun/predict_i2i_inpaint_2.1.py
Then run the file
examples/z_image_fun/predict_t2i_control_2.1.py
and
examples/z_image_fun/predict_i2i_inpaint_2.1.py
.
Runs of alibaba-pai Z-Image-Fun-Lora-Distill on huggingface.co
11.7K
Total runs
0
24-hour runs
120
3-day runs
339
7-day runs
32
30-day runs
More Information About Z-Image-Fun-Lora-Distill huggingface.co Model
Z-Image-Fun-Lora-Distill huggingface.co is an AI model on huggingface.co that provides Z-Image-Fun-Lora-Distill's model effect (), which can be used instantly with this alibaba-pai Z-Image-Fun-Lora-Distill model. huggingface.co supports a free trial of the Z-Image-Fun-Lora-Distill model, and also provides paid use of the Z-Image-Fun-Lora-Distill. Support call Z-Image-Fun-Lora-Distill model through api, including Node.js, Python, http.
Z-Image-Fun-Lora-Distill huggingface.co is an online trial and call api platform, which integrates Z-Image-Fun-Lora-Distill's modeling effects, including api services, and provides a free online trial of Z-Image-Fun-Lora-Distill, you can try Z-Image-Fun-Lora-Distill online for free by clicking the link below.
alibaba-pai Z-Image-Fun-Lora-Distill online free url in huggingface.co:
Z-Image-Fun-Lora-Distill is an open source model from GitHub that offers a free installation service, and any user can find Z-Image-Fun-Lora-Distill on GitHub to install. At the same time, huggingface.co provides the effect of Z-Image-Fun-Lora-Distill install, users can directly use Z-Image-Fun-Lora-Distill installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
Z-Image-Fun-Lora-Distill install url in huggingface.co: