# Loading an image to SAG pipeline
**URL:**
**Author:**  [@haobaiguy](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fhaobaiguy)%5C
**Post date:** [August 25, 2025, 12:35pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Floading-an-image-to-sag-pipeline%2F167744%2F1 "2025-08-25T12:35:49Z")
I realize that this is a deprecated pipeline, but I still want to give it a try in refining an existing image. Does anyone know how I can pass an image to StableDiffusionSAGPipeline?
I can tell you what I’ve tried, but I am keeping the question simple.
How can I pass an existing image (latent or minimally processed) to StableDiffusionSAGPipeline?
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [August 25, 2025, 3:41pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Floading-an-image-to-sag-pipeline%2F167744%2F2 "2025-08-25T15:41:02Z")
[Using an IP adapter](https://huggingface.co/docs/diffusers/v0.35.1/using-diffusers/ip_adapter) is relatively easy, but otherwise I think you will need to modify the pipeline.
```py
# pip install -U diffusers transformers accelerate torch torchvision safetensors
import torch
from diffusers import StableDiffusionSAGPipeline
from diffusers.utils import load_image
device = "cuda" if torch.cuda.is_available() else "cpu"
# SD 1.5 + SAG
pipe = StableDiffusionSAGPipeline.from_pretrained(
"stable-diffusion-v1-5/stable-diffusion-v1-5",
torch_dtype=torch.float16 if device == "cuda" else torch.float32,
use_safetensors=True,
).to(device)
# Load IP-Adapter for SD 1.5 (repo subfolder = "models")
pipe.load_ip_adapter(
"h94/IP-Adapter",
subfolder="models",
weight_name="ip-adapter_sd15.bin",
)
pipe.set_ip_adapter_scale(0.6) # 0=text only, 1=image only
# URL reference image
ref_url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/load_neg_embed.png"
ref_img = load_image(ref_url)
# Generate
g = torch.Generator(device="cpu").manual_seed(42)
image = pipe(
prompt="bear eats pizza, photorealistic, detailed",
negative_prompt="low quality, watermark, text",
ip_adapter_image=ref_img, # image conditioning
guidance_scale=1.0, # low CFG pairs well with SAG
sag_scale=0.75, # SAG strength
num_inference_steps=40,
generator=g,
).images[0]
image.save("out_sag_ip_adapter.png")
print("saved out_sag_ip_adapter.png")
```
---
**Author:**  [@haobaiguy](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fhaobaiguy)%5C
**Post date:** [August 26, 2025, 11:43am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Floading-an-image-to-sag-pipeline%2F167744%2F3 "2025-08-26T11:43:10Z")
You are a Boss!
I got something from the model, not what I wanted, but something. Most importantly, I learned a new line. Thanks!