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.
☆207Updated last month
Related projects ⓘ
Alternatives and complementary repositories for flux-fp8-api
- End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).☆266Updated last week
- SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models☆327Updated this week
- ☆407Updated 7 months ago
- Reference-Based Modulation (RB-Modulation)☆124Updated 2 months ago
- Accelerates Flux.1 image generation, just by using this node.☆107Updated last month
- Cog inference for flux models☆283Updated this week
- Various training scripts used to train bigasp☆68Updated 3 weeks ago
- An AI focused photo manipulation tool based on Gradio☆176Updated 3 weeks ago
- ☆46Updated 2 months ago
- The best OSS video generation models☆121Updated 3 weeks ago
- ☆123Updated last month
- JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for th…☆135Updated last month
- ComfyUI nodes to edit videos using Genmo Mochi☆245Updated 2 weeks ago
- Training-free Regional Prompting for Diffusion Transformers 🔥☆354Updated last week
- This repository implements the idea of "caption upsampling" from DALL-E 3 with Zephyr-7B and gathers results with SDXL.☆153Updated last year
- IP Adapter Instruct☆185Updated 3 months ago
- Official code for "RB-Modulation: Training-Free Personalization of Diffusion Models using Stochastic Optimal Control"☆341Updated 2 months ago
- [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising☆164Updated last month
- Faster generation with text-to-image diffusion models.☆194Updated last month
- ☆119Updated last month
- SSD-1B, an open-source text-to-image model, outperforming previous versions by being 50% smaller and 60% faster than SDXL.☆166Updated 7 months ago
- Official Repository of the paper "Trajectory Consistency Distillation"☆318Updated 6 months ago
- Memory optimized finetuning scripts for CogVideoX using TorchAO and DeepSpeed☆406Updated this week
- Experimental usage of stable-fast and TensorRT.☆200Updated 3 months ago
- T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!☆361Updated 2 months ago
- Official implementation of ⚡ Flash Diffusion ⚡: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation☆472Updated 4 months ago
- ☆144Updated this week
- [NeurIPS 2024] Boosting the performance of consistency models with PCM!☆364Updated 3 weeks ago
- text to image to generation: CogView3-Plus and CogView3(ECCV 2024)☆245Updated last month
- Rectified Flow Inversion (RF-Inversion)☆264Updated 3 weeks ago