This workflow generates a morphing video across 4 images, like the one below, from text prompts. You can fine-tune each image by changing its prompt, and the transition pattern can be adjusted. You will need to be a member of this site to download the ComfyUI workflow. Table of ContentsSoftwareStable Diffusion GUIHow this workflow worksOverviewImage…
Blog
SDXL vs Flux1.dev models comparison
SDXL and Flux1.dev are two popular local AI image models. Both have a relatively high native resolution of 1024×1024. Currently, more resources are available for SDXL, such as model training tools and ControlNet models, but those of the Flux model will likely catch up. Should you move on to the newest Flux model and delete…
Origami dance video (ComfyUI)
This workflow transforms any dance video into a video of dancing origami. The look and color of the origami can be customized. The background generally follows that of the input video, but you can customize it using the prompt to some extent. You will need to be a member of this site to download the…
How to run ComfyUI on Google Colab
ComfyUI is a popular way to run local Stable Diffusion and Flux AI image models. It is a great complement to AUTOMATIC1111 and Forge. Some workflows may require a good GPU to run. In this article, you will find instructions on how to run ComfyUI on Google Colab using the notebook I maintain. Table of…
Flux-CogVideo Text-to-Video workflow (ComfyUI)
This ComfyUI workflow uses the Flux AI model to generate a high-quality image, followed by image-to-video generation with CogVideo. The end result is a workflow that produces a video with a text prompt. The video quality is higher than using the original CogVideo text-to-video model. You need to be a member of this site to…
Animal dance video workflow (ComfyUI)
This workflow converts the subject of a dance video into an animal using Stable Diffusion. The following techniques will be used. You will learn/get:
How to run SD Forge WebUI on Google Colab
Stable Diffusion Forge WebUI has emerged as a popular way to run Stable Diffusion and Flux AI image models. It is optimized to run fast and pre-installed with many essential extensions. If you don’t have a powerful GPU card, you can run Forge on Google Colab. Table of ContentsWhat is SD Forge?Using SD Forge on…
How to direct motion in Kling AI video
Kling AI is one of the best online video generators that can turn any image into a video. Although Kling has its own text-to-image generator, it pairs with the Flux AI model really well, which can generate extremely high-quality images locally. When generating a video from an image, you describe the motion in the text…
On the phone
This beginner Flux workflow generates a retro photo of a housewife talking using an old-style phone. You will also find instructions to turn this photo into a video like the one below. Here’s how to create this image and video:
How to train Flux LoRA models
The Flux Dev AI model is a great leap forward in local Diffusion models. It delivers quality surpassing Stable Diffusion 1.5 and XL models. Like Stable Diffusion models, you can train LoRA models on top of Flux to inject custom characters and styles. In this post, I will provide a Google Colab notebook for training…