AuraFlow v0.3 is the fully open-sourced flow-based text-to-image generation model. The model was trained with more compute compared to the previous version, AuraFlow-v0.2.
Compared to AuraFlow-v0.2, the model is fine-tuned on more aesthetic datasets and now supports various aspect ratio, (now width and height up to 1536 pixels).
$ pip install transformers accelerate protobuf sentencepiece
$ pip install git+https://github.com/huggingface/diffusers.git
from diffusers import AuraFlowPipeline
import torch
pipeline = AuraFlowPipeline.from_pretrained(
"terminusresearch/auraflow-v0.3",
torch_dtype=torch.float16,
variant="fp16",
).to("cuda")
image = pipeline(
prompt="rempage of the iguana character riding F1, fast and furious, cinematic movie poster",
width=1536,
height=768,
num_inference_steps=50,
generator=torch.Generator().manual_seed(1),
guidance_scale=3.5,
).images[0]
image.save("output.png")
aura_flow_0.3.safetensors 16 GBtransformer/diffusion_pytorch_model-00001-of-00003.safetensors 10.0 GBtransformer/diffusion_pytorch_model-00001-of-00002.fp16.safetensors 9.9 GBtransformer/diffusion_pytorch_model-00002-of-00003.safetensors 9.9 GBtransformer/diffusion_pytorch_model-00003-of-00003.safetensors 7.5 GBtext_encoder/model.safetensors 4.9 GBtransformer/diffusion_pytorch_model-00002-of-00002.fp16.safetensors 3.8 GBtext_encoder/model.fp16.safetensors 3.0 GBvae/diffusion_pytorch_model.safetensors 335 MBvae/diffusion_pytorch_model.fp16.safetensors 167 MB有文件?提交种子。
提交种子