# Target\_size issue
**URL:**
**Author:**  [@iam-tsr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fiam-tsr)%5C
**Post date:** [September 28, 2025, 7:02am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftarget-size-issue%2F168739%2F1 "2025-09-28T07:02:20Z")
I am using ImageToImageTargetSize paramenter with InferenceClient
from huggingface\_hub.inference.\_generated.types.image\_to\_image import ImageToImageTargetSize
target\_size=ImageToImageTargetSize(256, 256)
But the output is still same as input image size. Can anyone help me to figure out what thing I am doing wrong?
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [September 28, 2025, 8:53am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftarget-size-issue%2F168739%2F2 "2025-09-28T08:53:37Z")
The parameter seems to be ignored…
Depending on the model, resolution constraints or the input image resolution may take precedence, causing the output resolution parameter to be ignored. Or is it a bug?
```py
from huggingface_hub import InferenceClient, ImageToImageTargetSize
client = InferenceClient(model="Qwen/Qwen-Image-Edit")
url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/edit_homepage.jpg" # (1312, 800)
img = client.image_to_image(
url,
prompt="cinematic lighting",
target_size=ImageToImageTargetSize(height=256, width=256),
provider="fal"
)
print(img.size) # (1312, 800)
img.save("out.jpg")
```
---
**Author:**  [@iam-tsr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fiam-tsr)%5C
**Post date:** [September 28, 2025, 9:18am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftarget-size-issue%2F168739%2F3 "2025-09-28T09:18:40Z")
I have read the full image to image inference repo files, there i find two output classes out of which `ImageToImageTargetSize` is defined in the main parameter class.
`ImageToImageOutput` is the other one which do the same functioning ig.
Here you can find it - [https://github.com/huggingface/huggingface\_hub/blob/main/src/huggingface\_hub/inference/\_generated/types/image\_to\_image.py](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/inference/%5C_generated/types/image_to_image.py)
I think it is a bug and I have reported it.
---
**Author:**  [@John6666](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FJohn6666)%5C
**Post date:** [September 28, 2025, 10:03am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftarget-size-issue%2F168739%2F4 "2025-09-28T10:03:37Z")
Similar behavior was observed with `prithivMLmods/Monochrome-Pencil`. If the size specification parameter doesn’t work in Flux Kontext’s LoRA, then there are probably very few Endpoints that support size specification…
Could it be that parameters aren’t being passed correctly when TGI uses Diffusers as the backend…? @michellehbn
---
**Author:**  [@iam-tsr](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fiam-tsr)%5C
**Post date:** [September 30, 2025, 3:55am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftarget-size-issue%2F168739%2F5 "2025-09-30T03:55:46Z")
The bug has been fixed and released in [`huggingface_hub==0.35.3`](https://github.com/huggingface/huggingface_hub/releases/tag/v0.35.3)
---
**Author:**  [@system](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsystem)%5C
**Post date:** [September 30, 2025, 3:56pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ftarget-size-issue%2F168739%2F6 "2025-09-30T15:56:15Z")
Closed on September 30, 2025, 3:56pm UTC
This topic was automatically closed 12 hours after the last reply. New replies are no longer allowed.