huggingface / huggingface/diffusers
FLUX.1-dev FP8 Example Code Cleanup
- Vorherrschende Sprache
- Python
- Sterne
- 34.5k
- Forks
- 7.3k
- Ø Merge
- 3 T. 3 Std.
- Gemergte PRs (30 T.)
- 91
Beschreibung
I was looking at the [FLUX.1-dev FP8 example code](https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux#single-file-loading-for-the-fluxtransformer2dmodel) in the documentation and noticed some unnecessary imports and variable declarations, which make it appear longer and cluttered. Here is the shorter version of the code I'm currently using. Please note that I'm not an expert, just trying to make it easier for anyone else looking to run the code.
```
import torch
from diffusers import FluxTransformer2DModel, FluxPipeline
from transformers import T5EncoderModel
from optimum.quanto import quantize, qfloat8, freeze
bfl_repo = "black-forest-labs/FLUX.1-dev"
transformer = FluxTransformer2DModel.from_single_file("https://huggingface.co/Kijai/flux-fp8/blob/main/flux1-dev-fp8.safetensors", torch_dtype=torch.bfloat16)
quantize(transformer, weights=qfloat8)
freeze(transformer)
text_encoder_2 = T5EncoderModel.from_pretrained(bfl_repo, subfolder="text_encoder_2", torch_dtype=torch.bfloat16)
quantize(text_encoder_2, weights=qfloat8)
freeze(text_encoder_2)
pipe = FluxPipeline.from_pretrained(bfl_repo, transformer=transformer, text_encoder_2=text_encoder_2, torch_dtype=torch.bfloat16)
pipe.enable_model_cpu_offload()
prompt = "A cat holding a sign that says hello world"
image = pipe(
prompt,
generator=torch.Generator("cpu").manual_seed(0)
).images[0]
image.save("flux-dev-fp8.png")
```
Optimizations made:
Removed unnecessary code and reduced the line count from 32 to 26.
Beitragsleitfaden
Rechercherichtung
Start with the linked FLUX.1-dev FP8 example in the Diffusers documentation and compare it with the shorter code shown in this issue. Remove the unnecessary imports and variable declarations while preserving the example's behavior, then verify that the documentation code remains runnable.
Vom Indexierungsmodell aus dem Issue-Text verfasst.
Bewertung
- Tech-Stack
- python, pytorch
- Bereich
- documentation
- Issue-Typ
- Dokumentation
- Schwierigkeit
- 1/5
- Geschätzter Aufwand
- 1-3 Stunden
- Aktivitätsstatus
- Veraltet
- Klarheit
- Klar beschrieben
- Anfängerfreundlichkeit
- 45/100