Bagheera PRO

bghira's activity

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

updated a model about 3 hours ago

SimpleTuner/Qwen-Image-2.1-LoRA-photo-aesthetics-v2

Text-to-Image • Updated about 1 hour ago

published a model about 3 hours ago

SimpleTuner/Qwen-Image-2.1-LoRA-photo-aesthetics-v2

Text-to-Image • Updated about 1 hour ago

updated a model about 3 hours ago

SimpleTuner/Qwen-Image-2.1-LoRA-experiments

Text-to-Image • Updated 36 minutes ago

liked a model about 20 hours ago

madebyollin/texture-fix-vae-for-qwen-image-2.1

0.3B • Updated 2 days ago • 940 • 23

updated a model about 23 hours ago

SimpleTuner/Qwen-Image-2.1-training-assistant-v2

Text-to-Image • Updated about 23 hours ago

published a model about 23 hours ago

SimpleTuner/Qwen-Image-2.1-training-assistant-v2

Text-to-Image • Updated about 23 hours ago

updated a model 1 day ago

SimpleTuner/Qwen-Image-2.1-LoRA-photo-aesthetics-v1

Text-to-Image • Updated 1 day ago • 1

published a model 1 day ago

SimpleTuner/Qwen-Image-2.1-LoRA-photo-aesthetics-v1

Text-to-Image • Updated 1 day ago • 1

published a model 2 days ago

SimpleTuner/Qwen-Image-2.1-LoRA-experiments

Text-to-Image • Updated 36 minutes ago

updated a model 3 days ago

SimpleTuner/Qwen-Image-2.1-training-assistant-v1

Text-to-Image • Updated 3 days ago

updated a dataset 3 days ago

webshart/qwen-image-2.1-generated-images

Preview • Updated 3 days ago • 227

published a dataset 3 days ago

webshart/qwen-image-2.1-generated-images

Preview • Updated 3 days ago • 227

published a model 3 days ago

SimpleTuner/Qwen-Image-2.1-training-assistant-v1

Text-to-Image • Updated 3 days ago

posted an update 11 days ago

view post

Post

38

Generated ~44 million Cosmos Reasoning captions for CC12M, now available here: webshart/cc12m-structured-captions

- webshart format, indexed with aspect bucketing metadata
- four captions per sample
- simple VLM output
- verbose caption
- a concise caption produced by passing the verbose caption through the model again to remove speculation and flowery language
- an ideogram4 style JSON schema


this used 8x H100 over about 6 days.

See translation

Reply

published a dataset 11 days ago

webshart/cc12m-structured-captions

Updated 11 days ago • 183

updated a dataset 11 days ago

webshart/cc12m-structured-captions

Updated 11 days ago • 183

New activity in lvladikov/Krea2-Turbo-Distill-4step-LoRA 11 days ago

too much Claude junk in the README

3

#10 opened 12 days ago by

bghira

updated a dataset 17 days ago

webshart/pseudo-camera-10k-structured

Updated 17 days ago • 101

published a dataset 17 days ago

webshart/pseudo-camera-10k-structured

Updated 17 days ago • 101

updated a dataset 17 days ago

terminusresearch/pseudo-camera-10k-structured-json

Viewer • Updated 17 days ago • 10k • 337