Downloads · 30 days
4
1% of all-time downloads
ft-sd15-human_face
quasar529/ft-sd15-human_face
ft-sd15-human_face is a text-to-image model from quasar529. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on ((Best quality)), ((masterpiece)), ((realistic)) human face photo capturing a person's gaze with a high definition, detai…
All-time downloads
456
Public
Repo size
88.9 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin97 MB · 98%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Access
- Public
- Created
- May 17, 2023
- Updated
- May 17, 2023
- SHA
- f8626539
Base models
Model card
From the Hugging Face model README
LoRA DreamBooth - MayIBorn/ft-sd15-human_face
These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on ((Best quality)), ((masterpiece)), ((realistic)) human face photo capturing a person's gaze with a high definition, detailed portrayal of the human face. The style emphasizes realism, using photography as the medium. The artwork showcases a close-up portrait, focusing on the subject's facial features. The color scheme reflects natural skin tones, lending authenticity to the depiction. using DreamBooth. You can find some example images in the following.
LoRA for the text encoder was enabled: True.
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Created
- May 17, 2023
- Updated
- May 17, 2023