|
--- |
|
tags: |
|
- text-to-image |
|
- stable-diffusion |
|
- lora |
|
- diffusers |
|
base_model: stabilityai/stable-diffusion-2-1-base |
|
license: mit |
|
library_name: diffusers |
|
--- |
|
|
|
# Model description |
|
|
|
Official SD21(base) Model of the paper [Trajectory Consistency Distillation](https://arxiv.org/abs/2402.19159). |
|
|
|
For more usage please found at [Project Page](https://huggingface.co/h1t/TCD-SDXL-LoRA/) |
|
|
|
Here is a simple example: |
|
|
|
```python |
|
import torch |
|
from diffusers import StableDiffusionPipeline, TCDScheduler |
|
|
|
device = "cuda" |
|
base_model_id = "stabilityai/stable-diffusion-2-1-base" |
|
tcd_lora_id = "h1t/TCD-SD21-base-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(0), |
|
).images[0] |
|
``` |
|
|
|
 |
|
|
