We can generate high-quality images by using both the SD 3.5 Large and SD 3.5 Turbo models, allowing for better refinement in the final image output.

Youtube Video Tricks to Master SD 3.5: https://www.youtube.com/watch?v=WNuxAyXFhb8

How It Works

So, how does it work? When you give Stable Diffusion a description, it starts from random noise and gradually refines the image. This process is called diffusion.

What’s unique about Stable Diffusion 3.5 is that it uses Rectified Flow Transformers. Think of this as taking the shortest, most direct path from noise to a final image. This means it can generate images faster and in fewer steps. and You can get awesome results—quickly!

Credit: https://comfyuiblog.com/comfyui-stable-diffusion-3-5-advanced-workflow-refine/

Resources

• Go to Please log in. https://huggingface.co/stabilityai/stable-diffusion-3.5-large You need to agree to share your contact information to access this model
• Download Stable Diffusion 3.5 Large or Stable Diffusion 3.5 Large Turbo to your models/checkpoint folder

https://huggingface.co/stabilityai/stable-diffusion-3.5-large/blob/main/sd3.5_large.safetensors

https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo/blob/main/sd3.5_large_turbo.safetensors

• https://huggingface.co/stabilityai/stable-diffusion-3-medium You need to agree to share your contact information to access this model
• Download clip_g.safetensors, clip_l.safetensors, and t5xxl_fp16.safetensors to your models/clip folder (you might have already downloaded them)

https://huggingface.co/stabilityai/stable-diffusion-3-medium/resolve/main/text_encoders/clip_g.safetensors

https://huggingface.co/stabilityai/stable-diffusion-3-medium/resolve/main/text_encoders/clip_l.safetensors

https://huggingface.co/stabilityai/stable-diffusion-3-medium/resolve/main/text_encoders/t5xxl_fp16.safetensors