TCD SD15 LoRA

🚀 TCD LoRA for Stable Diffusion v1.5

This is the official TCD LoRA for Stable Diffusion v1.5, which is based on the paper Trajectory Consistency Distillation. It provides a new approach for text - to - image generation.

🚀 Quick Start

Model Information

Usage Example

For more usage, please visit the Project Page.

Here is a simple example:

import torch
from diffusers import  StableDiffusionPipeline, TCDScheduler
device = "cuda"
base_model_id = "runwayml/stable-diffusion-v1-5"
tcd_lora_id = "h1t/TCD-SD15-LoRA"
pipe = StableDiffusionPipeline.from_pretrained(base_model_id, torch_dtype=torch.float16, variant="fp16").to(device)
pipe.scheduler = TCDScheduler.from_config(pipe.scheduler.config)
pipe.load_lora_weights(tcd_lora_id)
pipe.fuse_lora()
prompt = "Beautiful woman, bubblegum pink, lemon yellow, minty blue, futuristic, high-detail, epic composition, watercolor."
image = pipe(
    prompt=prompt,
    num_inference_steps=4,
    guidance_scale=0,
    # Eta (referred to as `gamma` in the paper) is used to control the stochasticity in every step.
    # A value of 0.3 often yields good results.
    # We recommend using a higher eta when increasing the number of inference steps.
    eta=0.3, 
    generator=torch.Generator(device=device).manual_seed(42),
).images[0]

📄 License

This project is licensed under the MIT license.