Instructions to use Kvikontent/midjourney-v6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Kvikontent/midjourney-v6 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("Kvikontent/midjourney-v6") prompt = "ed sheeran made of thnderstorm clouds, lights, thunder, rain, particles" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
dataset
Can you share the training dataset, thanks
Here it is, open for eveyone: https://drive.google.com/drive/folders/1DYknEHt0lyD_faz1vedRJkGbEGFtxQ6O?usp=drive_link
@toilaluan it is LoRA model and it don't need 100k images, it is actually trained on just 100 and in description 100k written only for "marketing:
@toilaluan it is LoRA model and it don't need 100k images, it is actually trained on just 100 and in description 100k written only for "marketing:
That's not very truthful...
Thats the small LoRA I've ever seen, and I think its inherently problematic to train AI on AI images. Not sure what the point is here.
hi, the link to MJ-V6 dataset (https://drive.google.com/drive/folders/1DYknEHt0lyD_faz1vedRJkGbEGFtxQ6O?usp=drive_link) shows no found 404, could you please send us one more link for access~~many thanks!!!