SurgFasT
Collection
Fast tracking surgical science with MedGemma • 3 items • Updated
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("danushkv/sd-cholec-inst", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Model Card for Model ID
This model is a fine-tuned version of stable-dffusion v1.5. The model is further consistency distilled to generate images within 1 inference step.
Model Details
Model Description
The model was trained on surgical images from the CholecInstanceSeg dataset. The text encoder used for training was the Text encoder from the MedSigLIP model which is also fine-tuned on the surgical dataset.
Please refer to the repo for use cases.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support