Stable Diffusion Community (Unofficial, Non-profit)

community

AI & ML interests

Enhance and upgrade SD-models

sd-community's activity

eienmojikiย 
posted an update 4 days ago
view post
Post
1924
๐Ÿช„ LayerDiffuse - Flux Version (Demo) ๐Ÿช„

LayerDiffuse - Transparent Image Layer Diffusion using Latent Transparency

Demo: eienmojiki/Flux-LayerDiffuse
ameerazam08ย 
posted an update 12 days ago
not-lainย 
posted an update 13 days ago
AtAndDevย 
posted an update 13 days ago
view post
Post
1841
everywhere i go i see his face
AtAndDevย 
posted an update 20 days ago
view post
Post
514
Deepseek gang on fire fr fr
AtAndDevย 
posted an update 22 days ago
view post
Post
1601
R1 is out! And with a lot of other R1 releated models...
not-lainย 
posted an update 25 days ago
view post
Post
1566
we now have more than 2000 public AI models using ModelHubMixin๐Ÿค—
not-lainย 
posted an update about 1 month ago
view post
Post
3989
Published a new blogpost ๐Ÿ“–
In this blogpost I have gone through the transformers' architecture emphasizing how shapes propagate throughout each layer.
๐Ÿ”— https://huggingface.co/blog/not-lain/tensor-dims
some interesting takeaways :
1aurentย 
posted an update about 1 month ago
ehristoforuย 
posted an update about 2 months ago
view post
Post
3252
โœ’๏ธ Ultraset - all-in-one dataset for SFT training in Alpaca format.
fluently-sets/ultraset

โ“ Ultraset is a comprehensive dataset for training Large Language Models (LLMs) using the SFT (instruction-based Fine-Tuning) method. This dataset consists of over 785 thousand entries in eight languages, including English, Russian, French, Italian, Spanish, German, Chinese, and Korean.

๐Ÿคฏ Ultraset solves the problem faced by users when selecting an appropriate dataset for LLM training. It combines various types of data required to enhance the model's skills in areas such as text writing and editing, mathematics, coding, biology, medicine, finance, and multilingualism.

๐Ÿค— For effective use of the dataset, it is recommended to utilize only the "instruction," "input," and "output" columns and train the model for 1-3 epochs. The dataset does not include DPO or Instruct data, making it suitable for training various types of LLM models.

โ‡๏ธ Ultraset is an excellent tool to improve your language model's skills in diverse knowledge areas.
AtAndDevย 
posted an update about 2 months ago
view post
Post
458
@s3nh Hey man check your discord! Got some news.
  • 4 replies
ยท
not-lainย 
posted an update 3 months ago
view post
Post
2312
ever wondered how you can make an API call to a visual-question-answering model without sending an image url ๐Ÿ‘€

you can do that by converting your local image to base64 and sending it to the API.

recently I made some changes to my library "loadimg" that allows you to make converting images to base64 a breeze.
๐Ÿ”— https://github.com/not-lain/loadimg

API request example ๐Ÿ› ๏ธ:
from loadimg import load_img
from huggingface_hub import InferenceClient

# or load a local image
my_b64_img = load_img(imgPath_url_pillow_or_numpy ,output_type="base64" ) 

client = InferenceClient(api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx")

messages = [
	{
		"role": "user",
		"content": [
			{
				"type": "text",
				"text": "Describe this image in one sentence."
			},
			{
				"type": "image_url",
				"image_url": {
					"url": my_b64_img # base64 allows using images without uploading them to the web
				}
			}
		]
	}
]

stream = client.chat.completions.create(
    model="meta-llama/Llama-3.2-11B-Vision-Instruct", 
	messages=messages, 
	max_tokens=500,
	stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content, end="")
KingNishย 
posted an update 4 months ago
KingNishย 
posted an update 5 months ago
view post
Post
8246
Exciting news! Introducing super-fast AI video assistant, currently in beta. With a minimum latency of under 500ms and an average latency of just 600ms.

DEMO LINK:
KingNish/Live-Video-Chat
  • 1 reply
ยท
KingNishย 
posted an update 5 months ago
KingNishย 
posted an update 5 months ago
view post
Post
3587
Mistral Nemo is better than many models in 1st grader level reasoning.