Downloads · 30 days
10
34% of all-time downloads
krea2_raw_768_102_1280_lora
kipgin/krea2_raw_768_102_1280_lora
krea2_raw_768_102_1280_lora is a text-to-image model from kipgin. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
LoRA (rank 32, alpha 32) train trên Krea-2 Raw bằng ai-toolkit / diffusiontrainer.
All-time downloads
29
Public
Repo size
361 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors361 MB · 100%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Access
- Public
- Created
- Aug 11, 2026
- Updated
- Aug 11, 2026
- SHA
- 6be0a236
Base models
Model card
From the Hugging Face model README
Krea-2 LoRA — PixelCraft UI
LoRA (rank 32, alpha 32) train trên Krea-2 Raw bằng ai-toolkit / diffusion_trainer.
- Trigger word:
PixelCraft UI - Steps: 1000, lr 1e-4, optimizer adamw8bit, bf16
- Resolutions: 768 / 1024 / 1280
Files
pytorch_lora_weights.safetensors— trọng số LoRAconfig.yaml— config train gốc
Cách dùng
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained("krea/Krea-2", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("kipgin/krea2_raw_768_102_1280_lora")
image = pipe("PixelCraft UI, a clean dashboard interface").images[0]
- Task
- Text-to-Image
- Library
- diffusers
- License
- other
- Created
- Aug 11, 2026
- Updated
- Aug 11, 2026