brivangl/midjourney-v6-llava
Viewer
• Updated
• 986k • 2.32k • 17
Roman Frigg
photoroman
AI & ML interests
None yet
Recent Activity
liked
a dataset 2 days ago
brivangl/midjourney-v6-llava published
a dataset 2 days ago
Photoroom/midjourney-v6-recap commented on an article 2 days ago
PRX Part 3 — Training a Text-to-Image Model in 24h! Organizations
liked a dataset 2 days ago
published a dataset 2 days ago
commented on PRX Part 3 — Training a Text-to-Image Model in 24h! 2 days ago
We have now released our Gemini 1.5 Flash captions (yes, Gemini 1.5 not 2.5 as incorrectly mentioned in the blog article) for the midjourney-v6 dataset. We also released captions generated with Qwen 3 VL 8B for the same dataset. During the speedrun we only used the Gemini captions though.
Here is the dataset: https://huggingface.co/datasets/Photoroom/midjourney-v6-recap
updated a dataset 2 days ago
upvoted an article 12 days ago
Article
PRX Part 3 — Training a Text-to-Image Model in 24h!
•
54
published an
article 12 days ago
Article
PRX Part 3 — Training a Text-to-Image Model in 24h!
•
54
upvoted an article about 1 month ago
Article
Training Design for Text-to-Image Models: Lessons from Ablations
•
69
published an
article about 1 month ago
Article
Training Design for Text-to-Image Models: Lessons from Ablations
•
69
Lora training instructions?
1
#2 opened 4 months ago
by
krigeta
Distorted images
5
#3 opened 4 months ago
by
HarryML
fix code snipped - import torch
1
#4 opened 4 months ago
by
retowyss
upvoted an article 4 months ago
Article
Text-to-image Architectural Experiments
•
54
published an
article 4 months ago
Article
Text-to-image Architectural Experiments
•
54
upvoted an article 4 months ago
Article
We’re open-sourcing our text-to-image model and the process behind it
•
95
published an
article 4 months ago
Article
We’re open-sourcing our text-to-image model and the process behind it
•
95