Text-to-Image
Diffusers
TensorBoard
StableDiffusionPipeline
stable-diffusion
stable-diffusion-diffusers
dreambooth
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("guaguale/model_kthv_vcg", dtype=torch.bfloat16, device_map="cuda")
prompt = "a male idol sks with blonde hair, wearing a black jacket and fringes on the sides of the jacket"
image = pipe(prompt).images[0]YAML Metadata Error:"base_model" with value "/mmu_vcg_ssd/liuhao12/workspace/1_diffusion/models/sd-zhuxiongwei-320nodes-task3_2-0612/checkpoint-28000/" is not valid. Use a model id from https://hf.co/models.
DreamBooth - guaguale/model_kthv_vcg
This is a dreambooth model derived from /mmu_vcg_ssd/liuhao12/workspace/1_diffusion/models/sd-zhuxiongwei-320nodes-task3_2-0612/checkpoint-28000/. The weights were trained on a male idol sks with blonde hair, wearing a black jacket and fringes on the sides of the jacket using DreamBooth. You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
- Downloads last month
- 1