Instructions to use coreco/seek.art_MEGA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use coreco/seek.art_MEGA with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("coreco/seek.art_MEGA", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Images from the model and from the seek.art website are different
#2
by duuuuuuuden - opened
Images created using a local UI and from the seek.art website are different with the same settings
I tried to use it with InvokeAI as inference tool and with AUTOMATIC1111s webui
On this screenshot you can see the settings I use and settings displayed on the website, they are the same
Anyway, thanks for your AMAZING work :D
I often use variations to tweak a seed I like, and those won't translate as I can't currently capture the "sub-seed", as it were. which is one reason they may be different. Another reason may be that seeds don't translate to Macs. In any case, I'm glad you're enjoying the model!