MeiYi's picture

MeiYi

natalie5

·

AI & ML interests

None yet

Recent Activity

new activity about 7 hours ago

aquif-ai/aquif-Image-14B:为什么和今年9月份CIVITAI的MAGIC WAN模型一摸一样？

liked a model 1 day ago

aquif-ai/aquif-Image-14B

new activity 1 day ago

aquif-ai/aquif-Image-14B:Can we get the fp16 variant please?

View all activity

Organizations

None yet

upvoted 2 collections 5 days ago

Video Foundation Models

A list of all the (usable) video generation diffusion models. Models that are not upto current standards are skipped. • 10 items • Updated 5 days ago • 1

Ovis-Image

Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering under stringent computational constraints. • 7 items • Updated 4 days ago • 5

upvoted 3 papers 5 days ago

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Paper • 2511.22699 • Published 10 days ago • 152

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published 6 days ago • 172

Glance: Accelerating Diffusion Models with 1 Sample

Paper • 2512.02899 • Published 5 days ago • 23

upvoted a paper 7 days ago

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Paper • 2511.20714 • Published 13 days ago • 45

upvoted a collection 9 days ago

Z-Image

4 items • Updated 7 days ago • 73

upvoted a paper 10 days ago

Video Generation Models Are Good Latent Reward Models

Paper • 2511.21541 • Published 11 days ago • 45

upvoted a paper 17 days ago

VIVAT: Virtuous Improving VAE Training through Artifact Mitigation

Paper • 2506.07863 • Published Jun 9 • 1

upvoted a paper 18 days ago

Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation

Paper • 2511.14993 • Published 19 days ago • 222

upvoted an article 19 days ago

Article

Text-to-image Architectural Experiments

24 days ago

•

37

upvoted 2 collections 20 days ago

Lychee-Uni-MoE 2.0

The second version of omnimodal large model Uni-MoE • 7 items • Updated 14 days ago • 6

Wan-NABLA

Collection of finetuned models for NABLA: Neighborhood Adaptive Block-Level Attention https://arxiv.org/abs/2507.13546 • 4 items • Updated Jul 25 • 5

upvoted 3 collections 22 days ago

Kandinsky 5.0 Video Lite

Kandinsky 5.0 Video Lite is a lightweight 2B model that generates up to 10-second SD videos from English and Russian prompts with high visual quality. • 9 items • Updated 13 days ago • 7

Kandinsky 5.0 Video Lite Diffusers

Kandinsky 5.0 Video Lite is a lightweight 2B model that generates up to 10-second SD videos from English and Russian prompts with high visual quality. • 8 items • Updated 13 days ago • 4

Kandinsky 5.0 Image Lite

Kandinsky 5.0 Image Lite is a 6B DiT-based model that generates and edits HD images from English and Russian text prompts with high visual quality. • 4 items • Updated 13 days ago • 13

upvoted a paper 23 days ago

One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models

Paper • 2511.10629 • Published 24 days ago • 122

upvoted 2 collections 23 days ago

Kandinsky 5.0 Video Pro Diffusers

Kandinsky 5.0 Video Pro is a 19B model that generates high-quality HD videos from English and Russian prompts with controllable camera motion. • 2 items • Updated 13 days ago • 6

Kandinsky 5.0 Video Pro

Kandinsky 5.0 Video Pro is a 19B model that generates high-quality HD videos from English and Russian prompts with controllable camera motion. • 5 items • Updated 13 days ago • 15

upvoted an article 26 days ago

Article

We’re open-sourcing our text-to-image model and the process behind it

26 days ago

•

73