cocokechun
Joined 8 years ago
Karma
139
Submissions
44
Member since
Jul 26
Recent submissions
Comment · 1 month ago
Comment · 4 months ago
Great question m8ven. It's actually using Seedance 2.0 behind the scene. It's essentially an agent to write scripts, create characters/scenes, create video clips and then edit them, without your manually doing these tasks at all.
Comment · 2 years ago
To push the development of the ComfyUI ecosystem, we are hosting the first contest dedicated to ComfyUI workflows! Anyone is welcomed to participate. Why should you participate?
- We have amazing judges like Scott DetWeiler, Olivio Sarikas (if you have watched any YouTube ComfyUI tutorials, you probably have watched their videos). - All the workflows for the contest can run on OpenArt’s cloud for free (coming soon later this week). You upload a workflow and others can run directly on OpenArt without hassles. - We have amazing cash prizes - 5 categories and 3 special awards.
Check out https://contest.openart.ai/ for more details.
Comment · 3 years ago
LoRA is one the fine-tuning methods. Compared to other methods like DreamBooth, Textual Inversion etc, it has benefits like smaller output file size, fewer training images required etc.
LoRA is particularly valuable for beginners, as it simplifies the process of adapting complex models for your specific needs without requiring extensive expertise in AI. Whether you're looking to enhance the performance of an image generation model or fine-tune a model for your specific need, LoRA can be a valuable ally in AI image generation journey.
Comment · 3 years ago
Have you ever felt confused about the meaning of parameters such as CFG scale, seed, or negative prompt? You’ve come to the right place. In this guide, we will give you the most complete explanation of each parameter with clear examples. You might think you already know everything, but we guarantee you will learn something new. Let’s get started and unlock the full potential of Stable Diffusion with these parameters together.
At OpenArt, we give creators access to all the best AI image and video models. New models launch constantly, each claimed to be the best, but our users never had a reliable answer to one basic question: *Which model should I use for my specific task?*
That is why we built OpenArt Arena. The Arena evaluates models across real use cases including film, advertising, animation, motion design, image and video editing, and lip sync.
We picked the criteria for each use case based on industry feedback. Then we had professional judges do blind test of two unlabeled outputs generated from the same prompt and reference materials. From there, we rank the models.
We’re not picking one “best” AI model.
We’re helping you find the best model for the work you’re trying to do.
The Arena is here: https://openart.ai/arena. If you have any questions - or think we have made the wrong tradeoffs - we’re happy to answer.