datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
multi-image-composition-instruction-following
Multi-Image Composition Instruction-Following
A large-scale multimodal dataset for multi-image composition via natural language instruction-following. Each case provides 2-3 input images (characters + scene) along with detailed Chinese instructions to compose them into a single photorealistic output image.
Designed for training and evaluating models on complex image composition tasks that require understanding of character identity preservation, pose generation, scene integration… See the full description on the dataset page: https://huggingface.co/datasets/obaydata/multi-image-composition-instruction-following.eco_compositionData sample for testing DL code
drugs-composition-indonesian-donut
Dataset Card for "drugs-composition-indonesian-donut"
Generate Custom Data
Please visit https://huggingface.co/spaces/jonathanjordan21/donut-labelling for the interface to generate custom data.
The data format is (.zip). Images and Labels are stored in separated .zip files.
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards
character-composition
Training code: https://github.com/tsiendragon/qwen-image-finetune
mask is used for add different weights to latent
model generated results:
landscape_llava_composition_datasetCompositionCapThis repository contains the dataset presented in FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity.
Mask Decoding
def decompress_mask(comp_string, height, width):
compressed_bytes = base64.b64decode(comp_string.encode('ascii'))
decompressed_bytes = gzip.decompress(compressed_bytes)
return np.frombuffer(decompressed_bytes, dtype=np.uint8).reshape((height, width))
compositional_controllandscape_cogvlm_composition_datasetComposition-benchmark