Instructions to use umikaze/umiseMixV2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use umikaze/umiseMixV2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("umikaze/umiseMixV2", 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
- Draw Things
- DiffusionBee
This model is a block-weighted merge of approximately 10-20 model
⚠Currently in V3. V2 models are deprecated. → https://civitai.com/models/11627/umisemixv3
This model was created based on the concept of simultaneous depiction of background and human figures. Errors in the model and Lora merged in the last update.
- Downloads last month
- 4