Stable Diffusion 3.5 Medium is Released
As mentioned in the previous blog post, Stable Diffusion 3.5 Medium is released. Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer with improvements (MMDiT-X) text-to-image […]
Introducing Stable Diffusion 3.5: Powerful AI Models for Enhanced Creativity and Efficiency
Stability AI has just unveiled Stable Diffusion 3.5, offering an exciting range of models designed for enhanced customization and use on consumer-grade hardware. The release […]
How to Update ComfyUI Manually on Windows
If you’re using ComfyUI and encounter an issue where the ComfyUI Manager fails to update the software, you can manually update it using a simple […]
How to Inpaint Hand More Efficiently in Web UI
AI hand generation is often flawed due to the intricate anatomy of hands, leading to distorted or inaccurate results. Inpainting helps fix these issues by […]
How to Fix onnxruntime_providers_cuda.dll LoadLibrary Error 126
If you’re diving into ONNX Runtime with CUDA and run into the LoadLibrary Error 126 with onnxruntime_providers_cuda.dll, don’t worry—it’s usually related to your CUDA or […]
How to Use ChatGPT to Write Flux.1 Prompts in T5 Style with an Input Image
In the world of AI and creative content generation, using advanced tools like Stable Diffusion models, particularly Flux.1, offers incredible opportunities to create stunning visuals. […]
How to Fix ComfyUI Running Slowly on Windows
When I tried using the Flux.1 model using ComfyUI, I found that it’s running very slowly even though I have a 3090 GPU with 24GB […]
How to Use Lora with Flux.1 Diffusion Model using ComfyUI
LoRA (Low-Rank Adaptation) is a technique used in Stable Diffusion to fine-tune models efficiently without requiring extensive computational resources. It allows users to adapt a […]
First Impressions of the Latest Flux.1 Stable Diffusion Model
The Flux.1 Stable Diffusion model has just dropped, and after spending some time with it, I’m pretty excited about what it brings to the table. […]
How to Install Comfyui-MusePose on Windows
According to the MusePose readme on github: MusePose is an image-to-video generation framework for virtual human under control signal such as pose. The current released model […]