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]An Ideogram 4 fp8 LoRA for making BBWs (big beautiful women).
There's probably a number of things wrong with it, it's my first Ideogram 4 LoRA. But it does appear to work. Trained using ai-toolkit on 147 images for 2000 steps. The ComfyUI workflow is in the .png image.
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for quarterturn/ideogram4-bbwhot-lora
Base model
ideogram-ai/ideogram-4-fp8
# Gated model: Login with a HF token with gated access permission hf auth login