SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation
Paper
•
2503.09641
•
Published
•
26
Finetrainers
non-profit
AI & ML interests
Accessible and delightful video model training and fine-tuning
Recent Activity
View all activity
finetrainers's activity
sayakpaul
authored
a
paper
10 days ago
sayakpaul
updated
a
collection
16 days ago
a-r-r-o-w
updated
a
model
17 days ago
a-r-r-o-w
published
a
model
17 days ago
a-r-r-o-w
updated
a
model
18 days ago
a-r-r-o-w
published
a
model
18 days ago
a-r-r-o-w
updated
a
model
19 days ago
a-r-r-o-w
published
a
model
19 days ago
a-r-r-o-w
updated
a
model
20 days ago
a-r-r-o-w
published
a
model
20 days ago
a-r-r-o-w
updated
a
model
21 days ago
a-r-r-o-w
published
a
model
21 days ago
a-r-r-o-w
updated
a
model
21 days ago
a-r-r-o-w
published
a
model
21 days ago
Post
3226
Inference-time scaling meets Flux.1-Dev (and others) 🔥
Presenting a simple re-implementation of "Inference-time scaling diffusion models beyond denoising steps" by Ma et al.
I did the simplest random search strategy, but results can potentially be improved with better-guided search methods.
Supports Gemini 2 Flash & Qwen2.5 as verifiers for "LLMGrading" 🤗
The steps are simple:
For each round:
1> Starting by sampling 2 starting noises with different seeds.
2> Score the generations w.r.t a metric.
3> Obtain the best generation from the current round.
If you have more compute budget, go to the next search round. Scale the noise pool (
This constitutes the random search method as done in the paper by Google DeepMind.
Code, more results, and a bunch of other stuff are in the repository. Check it out here: https://github.com/sayakpaul/tt-scale-flux/ 🤗
Presenting a simple re-implementation of "Inference-time scaling diffusion models beyond denoising steps" by Ma et al.
I did the simplest random search strategy, but results can potentially be improved with better-guided search methods.
Supports Gemini 2 Flash & Qwen2.5 as verifiers for "LLMGrading" 🤗
The steps are simple:
For each round:
1> Starting by sampling 2 starting noises with different seeds.
2> Score the generations w.r.t a metric.
3> Obtain the best generation from the current round.
If you have more compute budget, go to the next search round. Scale the noise pool (
2 ** search_round) and repeat 1 - 3.This constitutes the random search method as done in the paper by Google DeepMind.
Code, more results, and a bunch of other stuff are in the repository. Check it out here: https://github.com/sayakpaul/tt-scale-flux/ 🤗
Post
2020
We have been cooking a couple of fine-tuning runs on CogVideoX with finetrainers, smol datasets, and LoRA to generate cool video effects like crushing, dissolving, etc.
We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links:
* Models and datasets: https://huggingface.co/finetrainers
* finetrainers: https://github.com/a-r-r-o-w/finetrainers
* LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py
We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links:
* Models and datasets: https://huggingface.co/finetrainers
* finetrainers: https://github.com/a-r-r-o-w/finetrainers
* LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py
- 1 reply