How to use quarterturn/ideogram4-bbwhot-lora with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ideogram-ai/ideogram-4-fp8", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("quarterturn/ideogram4-bbwhot-lora") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0]
Title. LR 0.0001, adamw8bit, rank and alpha 16, do a test run with 512 res. Batch 2 minimum, use gradient if it's too much for your system.
· Sign up or log in to comment
