Wan-AI/Wan2.1-T2V-14B
Text-to-Video
•
Updated
•
207k
•
•
1.02k
Noah
notune
AI & ML interests
None yet
Recent Activity
liked
a model
11 days ago
Wan-AI/Wan2.1-T2V-14B
reacted
to
freddyaboulton's
post
with 🔥
3 months ago
Version 0.0.21 of gradio-pdf now properly loads chinese characters!
liked
a dataset
8 months ago
XAI/vlmsareblind
Organizations
None yet
notune's activity
liked
a
model
11 days ago
reacted to
freddyaboulton's
post with 🔥
3 months ago
Post
2296
Version 0.0.21 of gradio-pdf now properly loads chinese characters!
liked
a
dataset
8 months ago
liked
a
Space
9 months ago
liked
2
models
10 months ago
liked
a
Space
10 months ago
liked
2
models
10 months ago
liked
2
models
11 months ago
How to Fine Tune DBRX-Instruct?
7
#18 opened 12 months ago
by
elysiia
liked
a
Space
12 months ago
reacted to
vikhyatk's
post with ❤️
12 months ago
Post
3768
Just released a notebook showing how to finetune moondream: https://github.com/vikhyat/moondream/blob/main/notebooks/Finetuning.ipynb
reacted to
akhaliq's
post with 🚀
12 months ago
Post
2255
Mora
Enabling Generalist Video Generation via A Multi-Agent Framework
Mora: Enabling Generalist Video Generation via A Multi-Agent Framework (2403.13248)
Sora is the first large-scale generalist video generation model that garnered significant attention across society. Since its launch by OpenAI in February 2024, no other video generation models have paralleled {Sora}'s performance or its capacity to support a broad spectrum of video generation tasks. Additionally, there are only a few fully published video generation models, with the majority being closed-source. To address this gap, this paper proposes a new multi-agent framework Mora, which incorporates several advanced visual AI agents to replicate generalist video generation demonstrated by Sora. In particular, Mora can utilize multiple visual agents and successfully mimic Sora's video generation capabilities in various tasks, such as (1) text-to-video generation, (2) text-conditional image-to-video generation, (3) extend generated videos, (4) video-to-video editing, (5) connect videos and (6) simulate digital worlds. Our extensive experimental results show that Mora achieves performance that is proximate to that of Sora in various tasks. However, there exists an obvious performance gap between our work and Sora when assessed holistically. In summary, we hope this project can guide the future trajectory of video generation through collaborative AI agents.
Enabling Generalist Video Generation via A Multi-Agent Framework
Mora: Enabling Generalist Video Generation via A Multi-Agent Framework (2403.13248)
Sora is the first large-scale generalist video generation model that garnered significant attention across society. Since its launch by OpenAI in February 2024, no other video generation models have paralleled {Sora}'s performance or its capacity to support a broad spectrum of video generation tasks. Additionally, there are only a few fully published video generation models, with the majority being closed-source. To address this gap, this paper proposes a new multi-agent framework Mora, which incorporates several advanced visual AI agents to replicate generalist video generation demonstrated by Sora. In particular, Mora can utilize multiple visual agents and successfully mimic Sora's video generation capabilities in various tasks, such as (1) text-to-video generation, (2) text-conditional image-to-video generation, (3) extend generated videos, (4) video-to-video editing, (5) connect videos and (6) simulate digital worlds. Our extensive experimental results show that Mora achieves performance that is proximate to that of Sora in various tasks. However, there exists an obvious performance gap between our work and Sora when assessed holistically. In summary, we hope this project can guide the future trajectory of video generation through collaborative AI agents.
liked
a
Space
12 months ago
reacted to
akhaliq's
post with ❤️
about 1 year ago
Post
VisionLLaMA
A Unified LLaMA Interface for Vision Tasks
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks (2403.00522)
Large language models are built on top of a transformer-based architecture to process textual inputs. For example, the LLaMA stands out among many open-source implementations. Can the same transformer be used to process 2D images? In this paper, we answer this question by unveiling a LLaMA-like vision transformer in plain and pyramid forms, termed VisionLLaMA, which is tailored for this purpose. VisionLLaMA is a unified and generic modelling framework for solving most vision tasks. We extensively evaluate its effectiveness using typical pre-training paradigms in a good portion of downstream tasks of image perception and especially image generation. In many cases, VisionLLaMA have exhibited substantial gains over the previous state-of-the-art vision transformers. We believe that VisionLLaMA can serve as a strong new baseline model for vision generation and understanding.
A Unified LLaMA Interface for Vision Tasks
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks (2403.00522)
Large language models are built on top of a transformer-based architecture to process textual inputs. For example, the LLaMA stands out among many open-source implementations. Can the same transformer be used to process 2D images? In this paper, we answer this question by unveiling a LLaMA-like vision transformer in plain and pyramid forms, termed VisionLLaMA, which is tailored for this purpose. VisionLLaMA is a unified and generic modelling framework for solving most vision tasks. We extensively evaluate its effectiveness using typical pre-training paradigms in a good portion of downstream tasks of image perception and especially image generation. In many cases, VisionLLaMA have exhibited substantial gains over the previous state-of-the-art vision transformers. We believe that VisionLLaMA can serve as a strong new baseline model for vision generation and understanding.
reacted to
smangrul's
post with 🤯
about 1 year ago
Post
🚨 Now you can run Starcoder- 2 models locally on your Mac M1 Pro Apple Silicon with 16GB memory! 🧑🏽💻 ⚡️✨
Below is the UX with Twinny extension using bigcode/starcoder2-3b for FIM and codellama/CodeLlama-7b-Instruct-hf for chat. Dev tools is showing the prompt being sent to ollama server.
Starcoder-2 is now supported in
For more details, please go through the following tweet thread: https://x.com/sourab_m/status/1764583139798823235?s=20
Below is the UX with Twinny extension using bigcode/starcoder2-3b for FIM and codellama/CodeLlama-7b-Instruct-hf for chat. Dev tools is showing the prompt being sent to ollama server.
Starcoder-2 is now supported in
llama.cpp https://github.com/ggerganov/llama.cpp/pull/5795!cd llama.cpp
python convert-hf-to-gguf.py ../starcoder2-3b/ --outfile models/starcoder2-3b.gguf --outtype "f16"
./quantize models/starcoder2-3b.gguf models/starcoder2-3b-Q4_K_M.gguf Q4_K_MFor more details, please go through the following tweet thread: https://x.com/sourab_m/status/1764583139798823235?s=20
liked
a
model
about 1 year ago
reacted to
vladbogo's
post with 👍
about 1 year ago
Post
Genie is a new method from Google DeepMind that generates interactive, action-controllable virtual worlds from unlabelled internet videos using.
Keypoints:
* Genie leverages a spatiotemporal video tokenizer, an autoregressive dynamics model, and a latent action model to generate controllable video environments.
* The model is trained on video data alone, without requiring action labels, using unsupervised learning to infer latent actions between frames.
* The method restricts the size of the action vocabulary to 8 to ensure that the number of possible latent actions remains small.
* The dataset used for training is generated by filtering publicly available internet videos with specific criteria related to 2D platformer games for a total of 6.8M videos used for training.
Paper: Genie: Generative Interactive Environments (2402.15391)
Project page: https://sites.google.com/view/genie-2024/
More detailed overview in my blog: https://huggingface.co/blog/vladbogo/genie-generative-interactive-environments
Congrats to the authors for their work!
Keypoints:
* Genie leverages a spatiotemporal video tokenizer, an autoregressive dynamics model, and a latent action model to generate controllable video environments.
* The model is trained on video data alone, without requiring action labels, using unsupervised learning to infer latent actions between frames.
* The method restricts the size of the action vocabulary to 8 to ensure that the number of possible latent actions remains small.
* The dataset used for training is generated by filtering publicly available internet videos with specific criteria related to 2D platformer games for a total of 6.8M videos used for training.
Paper: Genie: Generative Interactive Environments (2402.15391)
Project page: https://sites.google.com/view/genie-2024/
More detailed overview in my blog: https://huggingface.co/blog/vladbogo/genie-generative-interactive-environments
Congrats to the authors for their work!
- 3 replies