Full-text search
Search in
Scope to owner or repo
617,350 results
Aleistar / Gengar_toy_example
README.md
dataset
1 matches
dhirajudhani / image
README.md
model
5 matches
tags: diffusers, flux, lora, replicate, text-to-image, en, base_model:black-forest-labs/FLUX.1-dev, base_model:adapter:black-forest-labs/FLUX.1-dev, license:other, region:us
22
# Image
⋯
32
You should use `dhiraj` to trigger the image generation.
⋯
42
pipeline.load_lora_weights('dhirajudhani/image', weight_name='lora.safetensors')
43
image = pipeline('your prompt').images[0]
nvidia / nemotron-ocr-v2
README.md
model
28 matches
tags: image, ocr, object recognition, text recognition, layout analysis, ingestion, multilingual, image-to-text, en, zh, ja, ko, ru, es, fr, de, it, nl, pt, license:other, region:us
36
...ptical character recognition (OCR) on complex real-world images. It integrates three core neural network modules: a dete...
38
...on speed and accuracy on both document and natural scene images.
⋯
59
...cy and high-speed extraction of textual information from images across multiple languages, making it ideal for powering ...
⋯
72
...ne for high-accuracy localization of text regions within images.
⋯
76
... and production-ready OCR for diverse document and scene images.
⋯
117
| Input Type & Format | Image (RGB, PNG/JPEG, float32/uint8), aggregation level (word, sentence, or paragraph) |
118
| Input Parameters (Two-Dimensional) | 3 x H x W (single image) or B x 3 x H x W (batch) |
119
| Input Range | [0, 1] (float32) or [0, 255] (uint8, auto-converted) |
120
| Other Properties | Handles both single images and batches. Automatic multi-scale resizing for best accuracy. |
xinyu1205 / recognize_anything_model
README.md
model
12 matches
tags: image tagging, image captioning, image-to-text, en, arxiv:2306.03514, arxiv:2303.05657, license:mit, region:us
12
...ognize-anything.github.io/">Recognize Anything: A Strong Image Tagging Model </a> and <a href="https://tag2text.github.i...
⋯
18
|  |
19
|:--:|
20
| <b> Pull figure from recognize-anything official repo | Image source: https://recognize-anything.github.io/ </b>|
⋯
26
...nize Anything Model~(RAM): a strong foundation model for image tagging. RAM makes a substantial step for large models in...
⋯
33
title={Recognize Anything: A Strong Image Tagging Model},
⋯
41
title={Tag2Text: Guiding Vision-Language Model via Image Tagging},
This file contains 3 more matches not shown. View all 9
matches in the full file.
kviai / Kvi-Upscale-V1
README.md
model
5 matches
nvidia / nemotron-page-elements-v3
README.md
model
16 matches
tags: image, detection, pdf, ingestion, yolox, object-detection, en, arxiv:2107.08430, license:other, region:us
22
*Preview of the model output on the example image.*
⋯
78
**Input Type(s)**: Image <br>
⋯
81
**Other Properties Related to Input**: Image size resized to `(1024, 1024)`
⋯
136
from PIL import Image
⋯
141
# Load image
142
path = "./example.png"
143
img = Image.open(path).convert("RGB")
nvidia / nemotron-table-structure-v1
README.md
model
23 matches
tags: image, detection, pdf, ingestion, yolox, object-detection, en, arxiv:2107.08430, license:other, region:us
23
*Preview of the model output on the example image.*
24
25
The input of this model is expected to be a table image. You can use the [Nemotron Page Element v3](https://huggingface....
⋯
29
...igned to identify and extract the structure of tables in images. Based on YOLOX, an anchor-free version of YOLO (You Onl...
⋯
62
The **Nemotron Table Structure v1** model specializes in analyzing images containing tables by:
⋯
70
3. Enable accurate extraction of tabular data from images
⋯
97
**Input Type(s)**: Image <br>
hazem-fahmy / AlexNet-GD
model
1 matches
kozak23 / Krea2_raw_fp8
model
1 matches
gymball / FatimaFellowship-UpsideDown
README.md
model
2 matches
unography / PP-HumanSegV1-Lite
README.md
model
2 matches
unography / PP-HumanSegV2-Lite
README.md
model
2 matches
johko / capdec_015
README.md
model
3 matches
johko / capdec_001
README.md
model
3 matches
johko / capdec_005
README.md
model
3 matches
johko / capdec_025
README.md
model
3 matches
