aredden / flux-fp8-apiLinks
Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.
☆281Updated last year
Alternatives and similar repositories for flux-fp8-api
Users that are interested in flux-fp8-api are comparing it to the libraries listed below
Sorting:
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆381Updated 4 months ago
- ☆282Updated 9 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆385Updated 3 months ago
- ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025 Oral)☆629Updated 7 months ago
- Generate long weighted prompt embeddings for Stable Diffusion☆139Updated 6 months ago
- ☆126Updated 7 months ago
- ☆436Updated last year
- ☆160Updated last week
- Faster generation with text-to-image diffusion models.☆228Updated 3 months ago
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆406Updated 7 months ago
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆498Updated 10 months ago
- Official Repository of the paper "Trajectory Consistency Distillation"☆351Updated last year
- Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"☆398Updated 7 months ago
- faster parallel inference of mochi-1 video generation model☆125Updated 7 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆205Updated 3 weeks ago
- AuraSR: GAN-based Super-Resolution for real-world☆511Updated 11 months ago
- SSD-1B, an open-source text-to-image model, outperforming previous versions by being 50% smaller and 60% faster than SDXL.☆177Updated last year
- The best OSS video generation models☆134Updated last year
- Various training scripts used to train bigasp☆104Updated 2 months ago
- LTXVideo Q8☆109Updated 10 months ago
- InstantID-ROME: Improved Identity-Preserving Generation in Seconds 🔥☆231Updated last year
- A detailed diagram laying out the full Flux.1 [dev] architecture as shared by Black Forest Labs at https://github.com/black-forest-labs/f…☆79Updated last year
- Implicit Style-Content Separation using B-LoRA☆389Updated 11 months ago
- Enhance-A-Video: Better Generated Video for Free☆576Updated 7 months ago
- IP Adapter Instruct☆208Updated last year
- Training-free Regional Prompting for Diffusion Transformers 🔥☆684Updated 10 months ago
- Making Flux go brrr on GPUs.☆146Updated 3 months ago
- See original repo here: https://github.com/google/RB-Modulation - ICLR 2025 (Oral)☆126Updated last year
- ☆445Updated last year
- Qwen-Image text to image lora trainer☆493Updated last week