Scaling Rectified Flow Transformers for High-Resolution Image Synthesis
Paper • 2403.03206 • Published • 71
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("armwaheed/stable-diffusion-3.5-medium-onnx", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Stable Diffusion 3.5 Medium ONNX
This ONNX version of Stable Diffusion 3.5 Medium was made from the PyTorch source model, using optimum-cli: Converting Stable Diffusion 3.5 Medium From PyTorch to ONNX.
Usage
Python Gradio: Stable Diffusion 3.5 Inpainting in ONNX
Model
Stable Diffusion 3.5 Medium is a Multimodal Diffusion Transformer with improvements (MMDiT-X) text-to-image model that features improved performance in image quality, typography, complex prompt understanding, and resource-efficiency.
Please note: This model is released under the Stability Community License. Visit Stability AI to learn or contact us for commercial licensing details.
Model Description
- Developed by: Stability AI
- Model type: MMDiT-X text-to-image generative model
- Model Description: This model generates images based on text prompts. It is a Multimodal Diffusion Transformer (https://arxiv.org/abs/2403.03206) with improvements that use three fixed, pretrained text encoders, with QK-normalization to improve training stability, and dual attention blocks in the first 12 transformer layers.
License
- Community License: Free for research, non-commercial, and commercial use for organizations or individuals with less than $1M in total annual revenue. More details can be found in the Community License Agreement. Read more at https://stability.ai/license.
- For individuals and organizations with annual revenue above $1M: please contact us to get an Enterprise License.
- Downloads last month
- 4