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.
☆282Updated 11 months ago
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).☆378Updated 4 months ago
- ☆284Updated 9 months ago
- https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching☆381Updated 2 months ago
- ☆161Updated 2 weeks ago
- Generate long weighted prompt embeddings for Stable Diffusion☆138Updated 5 months ago
- ☆437Updated last year
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆407Updated 7 months ago
- Cog inference for flux models☆364Updated 2 months ago
- Qwen-Image text to image lora trainer☆417Updated last week
- ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025 Oral)☆625Updated 6 months ago
- ☆126Updated 6 months ago
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆496Updated 9 months ago
- Various training scripts used to train bigasp☆102Updated last month
- Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"☆396Updated 6 months ago
- The best OSS video generation models☆134Updated 11 months ago
- Faster generation with text-to-image diffusion models.☆228Updated 3 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆205Updated this week
- ☆143Updated 7 months ago
- Official Repository of the paper "Trajectory Consistency Distillation"☆353Updated 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…☆78Updated 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
- See original repo here: https://github.com/google/RB-Modulation - ICLR 2025 (Oral)☆125Updated last year
- ☆136Updated last year
- InstantID-ROME: Improved Identity-Preserving Generation in Seconds 🔥☆231Updated last year
- Accelerates Flux.1 image generation, just by using this node.☆139Updated 9 months ago
- Training-free Regional Prompting for Diffusion Transformers 🔥☆683Updated 10 months ago
- AuraSR: GAN-based Super-Resolution for real-world☆511Updated 10 months ago
- faster parallel inference of mochi-1 video generation model☆125Updated 7 months ago
- Making Flux go brrr on GPUs.☆142Updated 2 months ago
- ☆566Updated 10 months ago