nDimensional: SD1.5 Models
Collection
Stable Diffusion v1.5 models by nDimensional. Includes 🤗exclusive models. • 9 items • Updated • 1
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("nDimensional/SciStyle_subset", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]
SciStyle
V1
Base Model: Stable Diffusion v1.5
Type: Fine-Tune
Clip Skip: 1
Medium: MultiMedium (Anime, Painting, Digital Art, 3D Render, Comic Illustration)
Caption Style: Natural Language + Booru style.
Dataset Size: Subset, ~1k images
Base Model: Stable Diffusion v1.5
Type: Fine-Tune
Clip Skip: 1
Medium: MultiMedium (Anime, Painting, Digital Art, 3D Render, Comic Illustration)
Caption Style: Natural Language + Booru style.
Dataset Size: Subset, ~1k images
V2
Base Model: Stable Diffusion v1.5
Type: Fine-Tune
Clip Skip: 1
Medium: MultiMedium
Caption Style: Natural Language + Booru Style
Dataset Size: ~4k images
Base Model: Stable Diffusion v1.5
Type: Fine-Tune
Clip Skip: 1
Medium: MultiMedium
Caption Style: Natural Language + Booru Style
Dataset Size: ~4k images
What's new in v2?
- More races/species from various Sci-fi and Fantasy universes.
- Started fine-tuning photo manipulation into the model for more abstract generations. This idea has since been abandoned and will be moved to its own dedicated photo manipulation model.
Science n' Dungeons
Base Model: Stable Diffusion v1.5
Type: Fine-Tune
Clip Skip: 1
Medium: MultiMedium
Caption Style: Natural Language + Booru Style
Dataset Size: ~4.5k images
Base Model: Stable Diffusion v1.5
Type: Fine-Tune
Clip Skip: 1
Medium: MultiMedium
Caption Style: Natural Language + Booru Style
Dataset Size: ~4.5k images
What's new in Science n' Dungeons?
- v2 with fine-tune on DnD race/monsters dataset
- Note: Less multimedium than v2
- Downloads last month
- 71