import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("ashen0209/Flux-Dev2Pro", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Flux-Dev2Pro
Flux-Dev2Pro finetunes the transformer of Flux-Dev to make LoRA training better.
As discussed in this blog https://medium.com/@zhiwangshi28/why-flux-lora-so-hard-to-train-and-how-to-overcome-it-a0c70bc59eaf, LoRA trained on Flux-Dev often yields bad results, because without guidance distillation the LoRA training is diverged from the original training process. Flux-Dev2Pro recovers Flux-pro from Flux-dev by finetuning the model for many steps. Two epoch of 3M high quality images have been trained.
The LoRA trained on Flux-Dev2pro yields a much better results when being applied on Flux-dev, just like LoRA trained on SDXL and being applied to SDXL-turbo/lightning.
To use this model, run:
from diffusers import FluxTransformer2DModel
transformer = FluxTransformer2DModel.from_pretrained("ashen0209/Flux-Dev2Pro", torch_dtype=torch.bfloat16)
- Downloads last month
- 52