kakaobrain/mindall-e
PyTorch implementation of a 1.3B text-to-image generation model trained on 14 million image-text pairs
PythonNOASSERTION
Issues
- 0
Project dependencies may have API risk issues
#24 opened by PyDeps - 2
Finetuning on custom dataset
#23 opened by INF800 - 0
Training hyperparameters
#11 opened by neverix - 2
text token index slice to N-1
#16 opened by j-min - 1
Comparison against GLIDE
#14 opened by MyUsernamee - 0
How to do inference from half image
#20 opened by thuangb - 3
Does zero-shot work in minDALL-E?
#6 opened by SeungyounShin - 1
CUDA out-of-memory
#19 opened by smittal10 - 0
Increasing positional embeddings text
#18 opened by ChristiaensBert - 2
How much VRAM is needed for this?
#17 opened by mjohanning99 - 2
- 4
질문있습니다. 파인튜닝 중에 image 에 대한 text 가 들어가지 않는데요
#9 opened by raki-1203 - 6
Notebook tweaks for Google Colab
#7 opened by woctezuma - 0
Script for VQGAN Finetuning
#15 opened by siddk - 3
complete images?
#8 opened by loboere - 1
Amazing work; models CDN?
#5 opened by johnpaulbin - 1
What training setup did you use?
#12 opened by rom1504 - 0
sampling in GPU with 12 GB memory
#1 opened by tackgeun