Downloads · 30 days
1.1K
14% of all-time downloads
Krea-2-LoRA-vintagetarot
krea/Krea-2-LoRA-vintagetarot
Krea-2-LoRA-vintagetarot is a text-to-image model from krea. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
A LoRA for Krea 2 — vintagetarot (trigger: vintage tarot style). - Trigger word: vintage tarot style - To be used on: krea/Krea-2-Turbo, the few-step distilled checkpoint shown in the previews above. - Trained on: kre…
All-time downloads
7.6K
Public
Repo size
544 MB
Likes
31
Public
Repo makeup
Click a slice to open those files.
.safetensors469 MB · 89%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Access
- Public
- Created
- Jun 20, 2026
- Updated
- Jun 23, 2026
- SHA
- 5fb7c2f1
Try a prompt
Base models
Model card
From the Hugging Face model README
Krea 2 LoRA — vintagetarot
A LoRA for Krea 2 — vintagetarot (trigger: vintage tarot style).
- Trigger word:
vintage tarot style - To be used on:
krea/Krea-2-Turbo, the few-step distilled checkpoint shown in the previews above. - Trained on:
krea/Krea-2-Raw. - Weights:
vintagetarot.safetensors - Previews: rendered on Turbo at 8 steps, guidance 0.0, LoRA weight
1.0.
Usage
import torch
from diffusers import Krea2Pipeline
pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.transformer.load_lora_adapter("krea/Krea-2-LoRA-vintagetarot", weight_name="vintagetarot.safetensors")
pipe.transformer.set_adapters("default", weights=1.0)
prompt = "A deer grazing in the forest, vintage tarot style"
image = pipe(prompt, num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("vintagetarot.png")
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Languages
- en
- Fal Ai
- live
- Created
- Jun 20, 2026
- Updated
- Jun 23, 2026