Downloads · 30 days
12
9% of all-time downloads
realHUmans
daceteate/realHUmans
realHUmans is a text-to-image model from daceteate. Use it when you need an image from a text prompt. It is set up for diffusers.
All-time downloads
135
Public
Repo size
230 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors229 MB · 99%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- Access
- Public
- Created
- Oct 2, 2025
- Updated
- Oct 2, 2025
- SHA
- 5b2068a1
Try a prompt
Base models
Model card
From the Hugging Face model README
MyLoRA for SDXL
<Gallery />Model description
Real Humans strength of "1.0" is good for general use, if the faces are not real enough, increase the weight. Also closeups with extremely realistic features, need higher weight than 1
Trigger word is "photo" and "portrait photo" forces closeups specially on higher weight
I see huge potential for merging, but didn't test yet, it's more of an experiment that went way better than expected so I shared it
Edit:
- Just noticed that's it's so good for selfie prompts "selfie portrait photo of..." at strength 1.5
- also noticed that I'm adding images with no prompts, feel free to ask for any missing one, I don't mind sharing
Trigger words
You should use photo to trigger the image generation.
You should use portrait photo to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Task
- Text-to-Image
- Library
- diffusers
- Fal Ai
- live
- Created
- Oct 2, 2025
- Updated
- Oct 2, 2025