Instructions to use carpedm20/flux2dev-fp8-transformer-rtx5090-sm120 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use carpedm20/flux2dev-fp8-transformer-rtx5090-sm120 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("carpedm20/flux2dev-fp8-transformer-rtx5090-sm120", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
flux2dev-fp8-transformer-rtx5090-sm120
Results and visual examples
FP8 FLUX.2-dev transformer weight shards for the RTX 5090 / SM120 runtime. This repository contains a transformer component, not a complete text-to-image pipeline. No saved image generation was bound to these exact shards in the recovered evidence.
Available build records: config.json, diffusion_pytorch_model.safetensors.index.json, meta.json, settings.json.
No checkpoint-matched photo gallery was located in the existing evidence reviewed for this update. The files and runtime records below are the available evidence; no visual quality claim is inferred from their presence.
Evidence provenance
This documentation update reuses saved results; it does not rerun inference or change weights. The starting repository revision is 002d8a7c8bfe. Captions distinguish model predictions, training diagnostics, and aggregate metrics. Qualitative examples are not a representative accuracy estimate.
- Downloads last month
- 420