import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Gerchegg/hyphoria_qwen_v1-Diffusers", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Hyphoria Qwen v1 Diffusers
Diffusers-packaged version of chapel/hyphoria_qwen_v1.0
using hyphoria_qwen_v1_bf16.safetensors as the custom Qwen-Image transformer.
Packaged analogously to Gerchegg/Qwen_FloVector_Hex_CharactersScenes_V1-Diffusers:
- base components from
Qwen/Qwen-Image:scheduler/,text_encoder/,tokenizer/,vae/ - custom transformer weights at
transformer/diffusion_pytorch_model.safetensors - Qwen-Image transformer config at
transformer/config.json
Source checkpoint: https://huggingface.co/chapel/hyphoria_qwen_v1.0
- Downloads last month
- -
Model tree for Gerchegg/hyphoria_qwen_v1-Diffusers
Base model
Qwen/Qwen-Image