pytorch / pytorch/TensorRT

🐛 [Bug] Flux does not produce the correct image

Open
#3,646 0 comments 0 reactions 1 assignee View on GitHub

@cehongwang is already working on this.

Since Jul 1, 2025.

bug story: LLM & Generative AI
Dominant language
Python
Stars
3k
Forks
410
Avg merge
3d 18h
Merged PRs (30d)
78

Description

Bug Description

To Reproduce

Steps to reproduce the behavior:

  1. use the latest flux demo python file
  2. generate the image using
seed = 42
warmup_prompt = "Beach and Kids"
images = pipe(
        warmup_prompt,
        output_type="pil",
        num_inference_steps=30,
        generator=torch.Generator("cuda").manual_seed(seed),
    ).images
  1. got the nonsense images.

Expected behavior

Environment

Build information about Torch-TensorRT can be found by turning on debug messages

  • Torch-TensorRT Version (e.g. 1.0.0):
  • PyTorch Version (e.g. 1.0):
  • CPU Architecture:
  • OS (e.g., Linux):
  • How you installed PyTorch (conda, pip, libtorch, source):
  • Build command you used (if compiling from source):
  • Are you using local sources or building from archives:
  • Python version:
  • CUDA version:
  • GPU models and configuration:
  • Any other relevant information:

Additional context

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.