import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("MiniMaxAI/MiniMax-H3", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ostris/minimax_h3_ref2va_jacked_lora")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]MiniMax H3 Ref2VA Jacked LoRA
This lora will make anyone jacked (huge muscles). This LoRA was trained while filming a tutorial How to Train a MiniMax H3 Ref2VA LoRA with AI Toolkit
Samples
Comfy UI
For Comfy UI, it is best to use this custom node with the workflow attached in the repo ComfyUI-AIToolkit-MiniMaxH3
- Downloads last month
- 311
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ostris/minimax_h3_ref2va_jacked_lora
Base model
MiniMaxAI/MiniMax-H3