🧨 Diffusers welcomes Stable Diffusion 3.5 Large
•
43
Sayak Paul
sayakpaul
AI & ML interests
Diffusion models, representation learning
Articles
Organizations
Posts
13
Post
2056
It's been a while we shipped native quantization support in
We currently support
This post is just a reminder of what's possible:
1. Loading a model with a quantization config
2. Saving a model with quantization config
3. Loading a pre-quantized model
4.
5. Training and loading LoRAs into quantized checkpoints
Docs:
https://huggingface.co/docs/diffusers/main/en/quantization/bitsandbytes
diffusers 🧨We currently support
bistandbytes as the official backend but using others like torchao is already very simple. This post is just a reminder of what's possible:
1. Loading a model with a quantization config
2. Saving a model with quantization config
3. Loading a pre-quantized model
4.
enable_model_cpu_offload()5. Training and loading LoRAs into quantized checkpoints
Docs:
https://huggingface.co/docs/diffusers/main/en/quantization/bitsandbytes
Post
2564
Did some little experimentation to resize pre-trained LoRAs on Flux. I explored two themes:
* Decrease the rank of a LoRA
* Increase the rank of a LoRA
The first one is helpful in reducing memory requirements if the LoRA is of a high rank, while the second one is merely an experiment. Another implication of this study is in the unification of LoRA ranks when you would like to
Check it out here:
sayakpaul/flux-lora-resizing
* Decrease the rank of a LoRA
* Increase the rank of a LoRA
The first one is helpful in reducing memory requirements if the LoRA is of a high rank, while the second one is merely an experiment. Another implication of this study is in the unification of LoRA ranks when you would like to
torch.compile() them. Check it out here:
sayakpaul/flux-lora-resizing
Collections
1
Provides a list of papers focusing on optimizing T2I diffusion models, targeting fewer timesteps, architecture optimization, and more.
-
Progressive Distillation for Fast Sampling of Diffusion Models
Paper • 2202.00512 • Published • 1 -
On Distillation of Guided Diffusion Models
Paper • 2210.03142 • Published -
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Paper • 2309.06380 • Published • 32 -
Consistency Models
Paper • 2303.01469 • Published • 8
spaces
19
Runtime error
15
📈
Demo Docker Gradio
Runtime error
🧨
Diffusers Docs QA Chatbot
Ask questions to the Diffusers documentation.
Build error
7
🧨
Convert Kerascv SD to Diffusers
Runtime error
🚀
Inpainting Tool
Build error
13
🐶
Generate Custom Pokemons with Stable Diffusion
Sleeping
8
⏰
Evaluate StableDiffusionPipeline with Different Schedulers
models
72
sayakpaul/mochi-lora
Text-to-Video
•
Updated
•
1
sayakpaul/mochi-lora-lr_1e-5-w_none-bit_no8bit
Updated
sayakpaul/mochi-lora-lr_1e-5-w_logit_normal-bit_no8bit
Updated
sayakpaul/mochi-lora-lr_1e-4-w_none-bit_no8bit
Updated
sayakpaul/mochi-lora-lr_1e-4-w_logit_normal-bit_no8bit
Updated
sayakpaul/optimizer_adamw_steps_1000_lr-schedule_cosine_with_restarts_learning-rate_5e-4_rank_
Text-to-Video
•
Updated
•
8
•
1
sayakpaul/optimizer_adamw_steps_1000_lr-schedule_cosine_with_restarts_learning-rate_3e-4_rank_
Text-to-Video
•
Updated
•
7
•
1
sayakpaul/optimizer_adamw_steps_1000_lr-schedule_cosine_with_restarts_learning-rate_1e-4_rank_
Text-to-Video
•
Updated
•
7
•
1
sayakpaul/optimizer_adamw_steps_1000_lr-schedule_cosine_with_restarts_learning-rate_5e-4
Text-to-Video
•
Updated
•
8
sayakpaul/optimizer_adamw_steps_1000_lr-schedule_cosine_with_restarts_learning-rate_3e-4
Text-to-Video
•
Updated
•
9
datasets
29
sayakpaul/pd12m-full
Viewer
•
Updated
•
10.8M
•
1.32k
•
6
sayakpaul/pick-a-pic-v2-unique-prompts
Viewer
•
Updated
•
59k
•
111
sayakpaul/sample-datasets
Viewer
•
Updated
•
6
•
23.5k
•
1
sayakpaul/poses-controlnet-dataset
Viewer
•
Updated
•
496
•
61
•
5
sayakpaul/torchao-diffusers
Updated
•
89
sayakpaul/pickapic_v2_webdataset
Viewer
•
Updated
•
8.7k
•
458
sayakpaul/generated-gemini-responses
Viewer
•
Updated
•
115
•
40
sayakpaul/no_robots_only_coding
Viewer
•
Updated
•
350
•
50
•
1
sayakpaul/diffusers-qa-chatbot-artifacts
Viewer
•
Updated
•
265k
•
227
•
1
sayakpaul/mgie-results
Viewer
•
Updated
•
8
•
49