103 8 197

Charles Bensimon

cbensimon

AI & ML interests

None yet

Recent Activity

replied to sebblers's post 4 days ago

Subscribed to pro a month ago because I wanted to get 25 minutes of zero gpu quota. I get error messages saying that I have exceeded quota on ALL spaces on this site. I haven't even used any quota. It says I have 25 minutes left to use. I can't try anything out! Been like this for a whole month now. What is this!? What did I sign up for exactly?

updated a Space 5 days ago

cbensimon/Real-Time-Text-to-Image-SDXL-Lightning

replied to Keltezaa's post 7 days ago

Other "Pro" members & staff. I am seriously considering of canceling my Pro subscription, unless this matter can be addressed. I subscribed to the Pro package for the use of the ZeroGPU, but the current recovery rate is not worth the money. I am supposed to get 5x more usage and or recovery. By my rough calculation the current recovery rate for GPU time spend is 18min per every 60sec of GPU usage. One of my "T-T-image" Spaces use about 45-50 seconds for each render. that gives 25-28 images At the current recover rate that is 2 images per hour, limited to 24 images per day. I may be wrong here or there may be something in my app.py code that is messing with with the usage time. currently it is set "@spaces.ZeroGPU(Duration=60)" If I reduce this I get an error if my render takes more time. (GPU task aborted, or error) The second thing that bothers me a bit is that some Errors, or failed image generation do not refund the usage. So if an image fails due to whatever error. It still gets added to the usage and as mentioned before recovers very slow. So at the end of the day If I get 15 usable images I consider myself lucky. As we all know, that you can prompt like a "boss" and the image dont always come out as you imagined or hoped. Thank you for taking the time to read my *RANT* - But I sincerely hope that We as paying users can get more value for money. Regrds.

View all activity

Organizations

cbensimon's activity

liked a dataset 13 days ago

modal-labs/dissolve

Viewer • Updated Nov 29, 2024 • 15 • 357 • 2

liked a model 13 days ago

finetrainers/pika-dissolve-v0

Text-to-Video • Updated 26 days ago • 271 • 7

liked a Space 14 days ago

1.67k

Chat With Janus-Pro-7B

🌍

A unified multimodal understanding and generation model.

liked a Space 19 days ago

1.49k

Hunyuan3D-2.0

🌍

Text-to-3D and Image-to-3D Generation

liked a Space 2 months ago

426

FLUXllama

🦀

FLUX 4-bit Quantization(just 8GB VRAM)

liked a Space 3 months ago

344

Logo In Context

🤗

Add a logo to anything

liked 4 Spaces 4 months ago

2.58k

IC Light V2

📈

Execute custom code from environment variable

587

Whisper Large V3

🤫

Transcribe audio or YouTube videos

1.71k

Stable Diffusion 3.5 Large

🏃

Generate images with SD3.5

1.03k

Joy Caption Pre Alpha

💬

Generate captions for images

liked 5 Spaces 5 months ago

1.8k

IDM VTON

👕

High-fidelity Virtual Try-on

salient-style-transfer

🖼

Transform images with artistic styles

228

Ultrapixel-demo

😻

Ultra-high resolution image synthesis

1.7k

PuLID-FLUX

🤗

Generate customized images using text and an ID image

257

Latent Navigation

🪐

liked a model 5 months ago

Shakker-Labs/FLUX.1-dev-LoRA-add-details

Text-to-Image • Updated Aug 30, 2024 • 78.1k • • 164

liked 4 Spaces 5 months ago

Flux1 Dev NF4

🦀

Generate images from text prompts

Real-Time Text-to-Image SDXL Lightning

⚡

192

FLUX GIFs

📽

Generate a GIF from a text prompt

124

One Step SDXL Comparison

🦶

Compare models that generate images ultra fast in 1 step