Sign In

TensorRT Flux.1 Dev conversion

6,000 BUZZ

Awarded
2
1
2
1

Started: Oct 12, 2024

tensorrtflux 1 dev

Bounty Type

Lora Creation

Base Model

Flux.1 D

Started

Oct 12, 2024

Deadline

Nov 12, 2024

flux-nv-blog-1280x680-1.jpg

About this bounty

Nvidia released a toolkit that speeds up models by 30%. Works great on SD3.

https://blogs.nvidia.com/blog/ai-decoded-flux-one/

I want this for Flux. I do not have enough local VRAM to convert the model. Can a hero get this done? Yes I'm aware of the tradeoffs with loras etc. I just want to improve raw doggin' flux dev. This hasn't been done yet to my knowledge, possibly because a float16 issue. From a HF comment:

Could this somehow help? https://github.com/microsoft/onnxscript/pull/1492

See also: https://github.com/microsoft/onnxruntime/issues/13001
and
: https://github.com/microsoft/onnxscript/issues/1462

To win this bounty:

  1. Convert the model and upload the FP16 Dev TensorRT to Civitai

  2. Post render comparisons using the TensorRT workflow

Comfy workflow:

https://github.com/comfyanonymous/ComfyUI_TensorRT

Entries

Discussion