laion-ai/laionide-v3

Public
GLIDE finetuned on LAION5B, then more on curated datasets.
56.2K runs

Run time and cost

Predictions run on Nvidia T4 GPU hardware. Predictions typically complete within 76 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Laionide (version 3)

Direct comparison to OpenAI's model using COCO captions

Shout out to stability.ai for donating the compute to laion needed for this to be possible.

Files:
- laionide-v3-base.pt

Inference:
- replicate
- colab
- locally

Results:
- comparison to openai W&B report

Notes:
- You can use laionide-v2-sr.pt to upscale the outputs from laionide-v3-base.pt.
- There are watermarks in some outputs. You can try to prompt engineer this away, but it isn't always possible. royalty free seems to work well.

Training details:
- finetuned laionide-v2-base.pt for 9 epochs on a subset of CC12M (~1.5 million pairs), COCO (~100K pairs), virtual genome (~100K pairs), and open images localized annotations (~800K pairs).
- 20% of unconditional/empty token, per the paper.

Replicate