aredden / flux-fp8-api
Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.
☆229Updated 3 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
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆304Updated 2 weeks ago
- ☆227Updated 2 weeks ago
- ☆412Updated 9 months ago
- Cog inference for flux models☆316Updated last week
- SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆585Updated this week
- Context parallel attention that accelerates DiT model inference with dynamic caching☆147Updated this week
- A pipeline parallel training script for diffusion models.☆415Updated this week
- ☆126Updated last month
- faster parallel inference of mochi-1 video generation model☆107Updated 3 weeks ago
- Various training scripts used to train bigasp☆75Updated 2 months ago
- Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model☆271Updated this week
- Enhance-A-Video: Better Generated Video for Free☆235Updated 3 weeks ago
- The best OSS video generation models☆130Updated 2 months ago
- Code release: https://github.com/google/RB-Modulation☆125Updated 4 months ago
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆375Updated 4 months ago
- ☆396Updated last month
- FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality☆189Updated 3 weeks ago
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆414Updated last month
- SSD-1B, an open-source text-to-image model, outperforming previous versions by being 50% smaller and 60% faster than SDXL.☆168Updated 9 months ago
- Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"☆354Updated 4 months ago
- Accelerates Flux.1 image generation, just by using this node.☆119Updated 3 weeks ago
- ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation (AAAI 2025)☆518Updated 6 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆175Updated 3 months ago
- ComfyUI nodes to edit videos using Genmo Mochi☆276Updated 2 months ago
- Training-free Regional Prompting for Diffusion Transformers 🔥☆518Updated last month
- Generate long weighted prompt embeddings for Stable Diffusion☆101Updated 3 months ago
- JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for th…☆268Updated last month
- Faster generation with text-to-image diffusion models.☆205Updated 3 months ago
- An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or…☆183Updated last week
- Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"☆394Updated 2 weeks ago