Downloads · 30 days
20
77% of all-time downloads
R_Vision_V6.0
chanacvg/R_Vision_V6.0
R_Vision_V6.0 is a text-to-image model from chanacvg. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as mit.
All-time downloads
26
Public
Repo size
2.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.1 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- mit
- Access
- Public
- Created
- Sep 1, 2026
- Updated
- Sep 1, 2026
- SHA
- 2ecda91d
Try a prompt
Base models
Model card
From the Hugging Face model README
Realistic_Vision_V6.0_R_fp16
<Gallery />Model description
This model is a fine-tuned version of Realistic_Vision_V6.0_R_fp16, the fp16 (half-precision) release of SG161222's Realistic Vision V6.0 checkpoint — a Stable Diffusion 1.5-based model built for realism and photorealism. The fp16 variant trims the file down to roughly 2.13 GB, about half the size of the standard fp32 release (~4 GB), making it faster to load and lighter on VRAM while keeping virtually the same image quality. The base model is designed for high-resolution photorealistic generation, with recommended output sizes including 896×896 for face portraits, 768×1024 for half/full body shots, and up to 1152×640 for wider full-body compositions. It's most commonly paired with the sd-vae-ft-mse-original VAE to sharpen detail and reduce artifacts, since this is a "noVAE"-style release that expects the VAE to be loaded separately
Download model
Download them in the Files & versions tab.
- Task
- Text-to-Image
- Library
- diffusers
- License
- mit
- Created
- Sep 1, 2026
- Updated
- Sep 1, 2026