RealVis Medium - Model for Realistic and Photorealistic Image Generation
Overview
RealVis Medium is a fine-tuned model with a focus on generating high-quality realistic and photorealistic images, based on SD3.5 Medium.
[!WARNING] Warning: This is not the final version of the model. Work on improving the model is still ongoing.
You can support me directly on my Boosty
Check my exclusive models on Mage: ParagonXL / NovaXL / NovaXL Lightning / NovaXL V2 / NovaXL Pony / NovaXL Pony Lightning / RealDreamXL / RealDreamXL Lightning
Example Images
Example 1, Example 2, Example 3, Example 4, Example 5
How to Use
For ComfyUI
Download all necessary model files and move them to the following paths:
-
From text_encoders folder, the files clip_g.safetensors, clip_l.safetensors, t5xxl_fp16.safetensors, or t5xxl_fp8_e4m3fn.safetensors to the location ComfyUI\models\clip
-
From transformer folder, the file diffusion_pytorch_model.safetensors to the location ComfyUI\models\unet
-
From vae folder, the file diffusion_pytorch_model.safetensors to the location ComfyUI\models\vae
Additionally, the repository contains two workflows for use in ComfyUI: RealVis Medium 1.0b Basic Workflow, RealVis Medium 1.0b Basic Workflow with Skip Layer Guidance
Usage & Limitations
- While this model can handle long prompts, you may observe artifacts on the edge of generations when T5 tokens go over 256. Pay attention to the token limits when using this model in your workflow, and shortern prompts if artifacts becomes too obvious.
- The medium model has a different training data distribution than the large model, so it may not respond to the same prompt similarly.
- We recommend sampling with Skip Layer Guidance for better structure and anatomy coherency.