# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("rkfg/Step1X-Edit-FP8", device_map="auto")Quick Links
Quantized version of Step1X-Edit with some layers left as BF16 for higher accuracy. Fork with memory optimizations to use with it: https://github.com/rkfg/Step1X-Edit
Model tree for rkfg/Step1X-Edit-FP8
Base model
stepfun-ai/Step1X-Edit
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-image" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-image", model="rkfg/Step1X-Edit-FP8")