sayakpaul / diffusers-torchao
End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
☆172Updated this week
Related projects: ⓘ
- Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x fast…☆105Updated this week
- An AI focused photo manipulation tool based on Gradio☆126Updated this week
- This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.☆149Updated 10 months ago
- ☆58Updated this week
- Build your own Face App with Stable Diffusion 2.1☆134Updated 3 weeks ago
- Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"☆311Updated last week
- ☆117Updated 3 months ago
- ☆118Updated 2 weeks ago
- ☆398Updated 5 months ago
- Faster generation with text-to-image diffusion models.☆181Updated 4 months ago
- SSD-1B, an open-source text-to-image model, outperforming previous versions by being 50% smaller and 60% faster than SDXL.☆164Updated 5 months ago
- ☆33Updated this week
- Diffusion Reinforcement Learning Library☆171Updated 7 months ago
- ☆74Updated 3 weeks ago
- Community ComfyUI workflows running on fal.ai☆53Updated 2 weeks ago
- IP Adapter Instruct☆175Updated last month
- ☆0Updated 9 months ago
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆411Updated 2 months ago
- ☆22Updated 7 months ago
- Official implementation of ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation☆436Updated 2 months ago
- Gradio UI for a Cog API☆62Updated 5 months ago
- ☆88Updated 8 months ago
- Implementation of "ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs"☆502Updated 8 months ago
- Official implementation of "AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising"☆144Updated last month
- sd3 dreambooth lora training book, adapted from the diffusers doc☆40Updated 3 months ago
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆340Updated 2 weeks ago
- Fine-tuning code for CLIP models☆120Updated this week
- Huggingface-compatible SDXL Unet implementation that is readily hackable☆381Updated last year
- This Flux latent upscaler workflow creates a lower-resolution initial pass, then advances to a second pass that upscales in latent space …☆59Updated last week
- Official Implementation of weights2weights☆98Updated last week