Text-to-Image
Diffusers
lora
template:diffusion-lora
PEFT
photo
identity
historical
counterculture
Futurism
Cubism
experimental
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Tongyi-MAI/Z-Image-Turbo", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("AlekseyCalvin/AleksandraEkster_ZiTLoRA_BySilverAgePoets")
prompt = "art"
image = pipe(prompt).images[0]Aleksandra Ekster / Constructivist Style Low Rank Adapter
For the Z-Image Turbo DiT Model
||| By SilverAgePoets.com |||
For generating stylized images reminiscent of iconic 1910s/1920s Constructivist avant-garde film/theatre stage set & costume designs by:
Aleksandra Ekster (1882 — 1949).
This is a very opinionated adapter imbuing a very idiosyncratic quasi-abstract stylization into figurative prompts.
Moreover, there is a high diversity across checkpoints, somewhat paralleling Ekster's own wide range of styles. We trained at rank64, using a fairly large and diverse self-curated dataset, and also altered its composition during training.
- Prompt
- art
- Prompt
- illustration by Aleksandra Ekster
- Prompt
- illustration by Aleksandra Ekster
- Prompt
- illustration by Aleksandra Ekster
- Prompt
- illustration by Aleksandra Ekster
- Prompt
- illustration by Aleksandra Ekster
Trigger words:
None required. (Trained without triggers.)
A few from among Ekster's stage designs used for this fine-tune:
A few from among Ekster's costume designs used for this fine-tune:
PHOTO OF ALEKSANDRA EKSTER:
- Downloads last month
- 27
Model tree for AlekseyCalvin/AleksandraEkster_ZiTLoRA_BySilverAgePoets
Base model
Tongyi-MAI/Z-Image-Turbo