you

megachad's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in nunchaku-tech/nunchaku-qwen-image-edit-2509 2 days ago

Whats the point of these if you still have to use the full-sized text_encoder?

#24 opened 2 days ago by

megachad

New activity in VAST-AI/UniRig 7 months ago

This doesn't run with huggingface code, it should not be here.

😔 1

2

#2 opened 8 months ago by

megachad

New activity in HighCWu/FLUX.1-dev-4bit about 1 year ago

Here is some code for using LORAs with this

3

#7 opened about 1 year ago by

megachad

How to achieve 4-bit quantization？

10

#6 opened over 1 year ago by

HUG-NAN

Questions about LoRA

2

#5 opened over 1 year ago by

tungdop2

Quantization scripts

13

#1 opened over 1 year ago by

WaveCut

New activity in KingNish/Realtime-FLUX over 1 year ago

comfyui implementation?

🤗 2

5

#1 opened over 1 year ago by

MayensGuds

New activity in p1atdev/FLUX.1-schnell-t5-xxl-quanto over 1 year ago

How to inference

1

#2 opened over 1 year ago by

zdxpan

New activity in coqui/XTTS-v2 over 1 year ago

Inference (Streaming)

5

#59 opened over 1 year ago by

hxrdxk

New activity in HighCWu/FLUX.1-dev-4bit over 1 year ago

Img2img works with this

1

#4 opened over 1 year ago by

megachad

New activity in black-forest-labs/FLUX.1-dev over 1 year ago

Is there any way to improve inference time?

3

#68 opened over 1 year ago by

winvin

New activity in Kijai/flux-fp8 over 1 year ago

quite slow to load the fp8 model

👍 4

11

#21 opened over 1 year ago by

gpt3eth

New activity in tuner007/pegasus_paraphrase about 3 years ago

This rephraser replaces words with 800 numbers. Extremely undesirable.

#9 opened about 3 years ago by

megachad