IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models
Paper
•
2501.13920
•
Published
•
12
Diffusers Pipelines Library for Stable Diffusion
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
sd-diffusers-pipelines-library's activity
Paper99
authored
a
paper
1 day ago
sunovivid
authored
a
paper
about 2 months ago
rizavelioglu
posted
an
update
about 2 months ago
Post
1352
Introducing Virtual Try-Off (VTOFF), a novel task focused on generating standardized garment images from single photos of clothed individuals. Unlike traditional Virtual Try-On (VTON), which digitally dresses models, VTOFF aims to extract a canonical garment image, posing unique challenges in capturing garment shape, texture, and intricate patterns.
Try it out: rizavelioglu/tryoffdiff
Paper: TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models (2411.18350)
Project page: https://rizavelioglu.github.io/tryoffdiff
Try it out: rizavelioglu/tryoffdiff
Paper: TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models (2411.18350)
Project page: https://rizavelioglu.github.io/tryoffdiff
-
- 1 reply
rizavelioglu
authored
a
paper
about 2 months ago
noamrot
authored
a
paper
about 2 months ago
MingZhong
authored
2
papers
4 months ago
shunk031
authored
a
paper
4 months ago
Paper99
authored
a
paper
4 months ago
susunghong
authored
a
paper
6 months ago
Royir
authored
a
paper
6 months ago
Royir
authored
a
paper
7 months ago
potamides
authored
a
paper
8 months ago
A-suozhang
authored
a
paper
8 months ago
potamides
authored
a
paper
8 months ago
A-suozhang
authored
2
papers
8 months ago
Post
4940
OpenELM in Core ML
Apple recently released a set of efficient LLMs in sizes varying between 270M and 3B parameters. Their quality, according to benchmarks, is similar to OLMo models of comparable size, but they required half the pre-training tokens because they use layer-wise scaling, where the number of attention heads increases in deeper layers.
I converted these models to Core ML, for use on Apple Silicon, using this script: https://gist.github.com/pcuenca/23cd08443460bc90854e2a6f0f575084. The converted models were uploaded to this community in the Hub for anyone that wants to integrate inside their apps: corenet-community/openelm-core-ml-6630c6b19268a5d878cfd194
The conversion was done with the following parameters:
- Precision: float32.
- Sequence length: fixed to 128.
With swift-transformers (https://github.com/huggingface/swift-transformers), I'm getting about 56 tok/s with the 270M on my M1 Max, and 6.5 with the largest 3B model. These speeds could be improved by converting to
I'm also looking at optimizing inference using an experimental kv cache in swift-transformers. It's a bit tricky because the layers have varying number of attention heads, but I'm curious to see how much this feature can accelerate performance in this model family :)
Regarding the instruct fine-tuned models, I don't know the chat template that was used. The models use the Llama 2 tokenizer, but the Llama 2 chat template, or the default Alignment Handbook one that was used to train, are not recognized. Any ideas on this welcome!
Apple recently released a set of efficient LLMs in sizes varying between 270M and 3B parameters. Their quality, according to benchmarks, is similar to OLMo models of comparable size, but they required half the pre-training tokens because they use layer-wise scaling, where the number of attention heads increases in deeper layers.
I converted these models to Core ML, for use on Apple Silicon, using this script: https://gist.github.com/pcuenca/23cd08443460bc90854e2a6f0f575084. The converted models were uploaded to this community in the Hub for anyone that wants to integrate inside their apps: corenet-community/openelm-core-ml-6630c6b19268a5d878cfd194
The conversion was done with the following parameters:
- Precision: float32.
- Sequence length: fixed to 128.
With swift-transformers (https://github.com/huggingface/swift-transformers), I'm getting about 56 tok/s with the 270M on my M1 Max, and 6.5 with the largest 3B model. These speeds could be improved by converting to
float16. However, there's some precision loss somewhere and generation doesn't work in float16 mode yet. I'm looking into this and will keep you posted! Or take a look at this issue if you'd like to help: https://github.com/huggingface/swift-transformers/issues/95I'm also looking at optimizing inference using an experimental kv cache in swift-transformers. It's a bit tricky because the layers have varying number of attention heads, but I'm curious to see how much this feature can accelerate performance in this model family :)
Regarding the instruct fine-tuned models, I don't know the chat template that was used. The models use the Llama 2 tokenizer, but the Llama 2 chat template, or the default Alignment Handbook one that was used to train, are not recognized. Any ideas on this welcome!
- 4 replies
noamrot
authored
a
paper
9 months ago
rizavelioglu
authored
a
paper
10 months ago