IP Composer

posted an update 9 months ago

Post

18225

Self-Forcing - a real-time video distilled model from Wan 2.1 by @adobe is out, and they open sourced it 🐐

I've built a live real time demo on Spaces 📹💨

multimodalart/self-forcing

6 replies

·

linoyts

posted an update 10 months ago

Post

17938

FramePack is hands down one of the best OS releases in video generation 🙇🏻‍♀️🤯
✅ fully open sourced + amazing quality + reduced memory + improved speed
but more even - its gonna facilitate *soooo* many downstream applications
like this version adapted for landscape rotation 👇https://huggingface.co/spaces/tori29umai/FramePack_rotate_landscape

3 replies

·

linoyts

posted an update 11 months ago

Post

3245

We just shipped HiDream Image LoRA fine-tuning to diffusers🧨

HiDream's sota capabilities (and mit license) bring a lot of potential to explore with fine-tunes 🔥

- more upgrades and features soon!
- code, weights and config example 👇

🧶Yarn art lora: linoyts/HiDream-yarn-art-LoRA
code: https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_hidream.md

2 replies

·

updated a Space 11 months ago

IP Composer

plug-and-play with visual concepts

linoyts

published a Space 11 months ago

IP Composer

plug-and-play with visual concepts

linoyts

updated a Space 11 months ago

IP Composer

plug-and-play with visual concepts

saradorfman

updated a Space 11 months ago

IP Composer

plug-and-play with visual concepts

linoyts

in IP-composer/ip-composer 11 months ago

add option for new user provided concepts

#4 opened 11 months ago by

make only concept 1 input in front tab

#3 opened 11 months ago by

updated a Space 11 months ago

README

🐨

linoyts

published a Space 11 months ago

README

🐨

linoyts

in IP-composer/ip-composer 12 months ago

initial ui changes

#2 opened 12 months ago by

Create app.py

#1 opened 12 months ago by

Paper • 2501.06751 • Published Jan 12, 2025 • 32

rinong

authored a paper about 1 year ago

Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models

rinong

authored 2 papers over 1 year ago

ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation

Paper • 2410.01731 • Published Oct 2, 2024 • 16

TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models

Paper • 2408.00735 • Published Aug 1, 2024 • 16

posted an update over 1 year ago

Post

35604

New feature 🔥
Image models and LoRAs now have little previews 🤏

If you don't know where to start to find them, I invite you to browse cool LoRAs in the profile of some amazing fine-tuners: @artificialguybr , @alvdansen , @DoctorDiffusion , @e-n-v-y , @KappaNeuro @ostris

3 replies

·

posted an update almost 2 years ago

Post

28621

The first open Stable Diffusion 3-like architecture model is JUST out 💣 - but it is not SD3! 🤔

It is Tencent-Hunyuan/HunyuanDiT by Tencent, a 1.5B parameter DiT (diffusion transformer) text-to-image model 🖼️✨, trained with multi-lingual CLIP + multi-lingual T5 text-encoders for english 🤝 chinese understanding

Try it out by yourself here ▶️ https://huggingface.co/spaces/multimodalart/HunyuanDiT
(a bit too slow as the model is chunky and the research code isn't super optimized for inference speed yet)

In the paper they claim to be SOTA open source based on human preference evaluation!