diffusers-internal-dev/gemini-prompt-expander
Updated
•
15
•
1
AI & ML interests
None defined yet.
Recent Activity
View all activity
sayakpaul
updated
2
models
2 days ago
sayakpaul
updated
a
model
19 days ago
sayakpaul
published
a
model
19 days ago
YiYiXu
updated
a
model
about 1 month ago
YiYiXu
published
a
model
about 1 month ago
sayakpaul
published
2
models
about 1 month ago
sayakpaul
updated
a
Space
about 1 month ago
sayakpaul
published
a
Space
about 1 month ago
sayakpaul
updated
a
model
about 2 months ago
sayakpaul
published
a
model
about 2 months ago
a-r-r-o-w
updated
a
model
about 2 months ago
a-r-r-o-w
published
a
model
about 2 months ago
a-r-r-o-w
updated
a
model
about 2 months ago
a-r-r-o-w
published
a
model
about 2 months ago
Post
1310
Fast LoRA inference for Flux with Diffusers and PEFT 🚨
There are great materials that demonstrate how to optimize inference for popular image generation models, such as Flux. However, very few cover how to serve LoRAs fast, despite LoRAs being an inseparable part of their adoption.
In our latest post, @BenjaminB and I show different techniques to optimize LoRA inference for the Flux family of models for image generation. Our recipe includes the use of:
1.
2. Flash Attention 3 (when compatible)
3. Dynamic FP8 weight quantization (when compatible)
4. Hotswapping for avoiding recompilation during swapping new LoRAs 🤯
We have tested our recipe with Flux.1-Dev on both H100 and RTX 4090. We achieve at least a *2x speedup* in either of the GPUs. We believe our recipe is grounded in the reality of how LoRA-based use cases are generally served. So, we hope this will be beneficial to the community 🤗
Even though our recipe was tested primarily with NVIDIA GPUs, it should also work with AMD GPUs.
Learn the details and the full code here:
https://huggingface.co/blog/lora-fast
There are great materials that demonstrate how to optimize inference for popular image generation models, such as Flux. However, very few cover how to serve LoRAs fast, despite LoRAs being an inseparable part of their adoption.
In our latest post, @BenjaminB and I show different techniques to optimize LoRA inference for the Flux family of models for image generation. Our recipe includes the use of:
1.
torch.compile2. Flash Attention 3 (when compatible)
3. Dynamic FP8 weight quantization (when compatible)
4. Hotswapping for avoiding recompilation during swapping new LoRAs 🤯
We have tested our recipe with Flux.1-Dev on both H100 and RTX 4090. We achieve at least a *2x speedup* in either of the GPUs. We believe our recipe is grounded in the reality of how LoRA-based use cases are generally served. So, we hope this will be beneficial to the community 🤗
Even though our recipe was tested primarily with NVIDIA GPUs, it should also work with AMD GPUs.
Learn the details and the full code here:
https://huggingface.co/blog/lora-fast
a-r-r-o-w
updated
a
model
about 2 months ago
multimodalart
posted
an
update
3 months ago
Post
15243
Self-Forcing - a real-time video distilled model from Wan 2.1 by
@adobe
is out, and they open sourced it 🐐
I've built a live real time demo on Spaces 📹💨
multimodalart/self-forcing
I've built a live real time demo on Spaces 📹💨
multimodalart/self-forcing
-
- 6 replies
Post
2813
Diffusers supports a good variety of quantization backends. It can be challenging to navigate through them, given the complex nature of diffusion pipelines in general.
So, @derekl35 set out to write a comprehensive guide that puts users in the front seat. Explore the different backends we support, learn the trade-offs they offer, and finally, check out the cool space we built that lets you compare quantization results.
Give it a go here:
https://lnkd.in/gf8Pi4-2
So, @derekl35 set out to write a comprehensive guide that puts users in the front seat. Explore the different backends we support, learn the trade-offs they offer, and finally, check out the cool space we built that lets you compare quantization results.
Give it a go here:
https://lnkd.in/gf8Pi4-2