Get live statistics and analysis of Travis Davids's profile on X / Twitter

I've had early access to @Kling_ai brand new 2.0 video model and done extensive testing and trust me when I say that this model upgrade is AMAZING!!! 🔥 The amount of incredible dynamic action that you can generate now is next level. If you want to make things go fast, the new model completely excels at this, movement looks very natural and fluid. This is a major release for Kling! Here is a collection of some clips I've generated with the 2.0 model.

There is a ridiculous amount of creative use cases with @pika_labs Pikaframes and I feel like I'm still scratching the surface. From generating opening titles, ink splash animations, to making someone age. It's honestly one of the best keyframing tools in the world of AI. Here are some creative use cases that I've generated that you can try 👍👍

I created a burger commercial using AI. Introducing THE SCORCHER! The Worlds hottest burger! Images created with @freepik MYSTIC and brought to life with @LumaLabsAI. Logos created with @ideogram_ai Music generated with @udiomusic and narration by @elevenlabsio

This is BLITZ 🏍️ starring myself. I've tested a workflow that combines two of the best AI image editing models right now, Nano Banana and Seedream 4. Using these together feels like a superpower. Seedream 4 for instance generates much more dynamic camera angles BUT Nano Banana does a better job with overall consistency, so utilizing both is super beneficial. I wanted to create a sequence where I'm riding a Cyberbike with an electric booster that overclocks the motor to deliver short, high-risk bursts of extreme speed. The location is a white sand desert. I decided to also test @Hailuo_AI start and end frame feature which in my opinion is one of the best since it understands so much about context and camera movement. Start and ends frames let you have much better control over camera movement but where Hailuo truly excels is that it understands speed and camera shake which are essential for any fast paced action sequences. The music was generated with Suno 4.5+ and some additional sound effects like the bike and wind in the desert were sourced from Artlist. Edited with Capcut. There's some more tips and tricks in the thread 👍👍

Yes, @runwayml Aleph is awesome! I tend to always test very stylized imagery since AI can handle photorealism quite easily BUT I wanted to reverse my experimentation and start with something stylized and see if Aleph can actually make it look photorealistic. It actually did it and it still kept the same reduced FPS rate that was present on the stylized video. I did however choose to give it a bit more context. The fact that all of the movement remains intact is crazy to witness. This feels like video inpainting/style transfer on steroids. My preference for this particular example would still be stylized but it's awesome you can just turn it into something realistic as well. 5 seconds is unfortunately a limitation but knowing Runway we will get much longer durations at some point. There are probably so many use cases to explore with Aleph that it will blow our minds.

By combining @pika_labs Pikaframes and @freepik, I now have the magical ability to jump through space and time and in this example, music becomes a transformative element teleporting this woman to a new location. This is how it's done. 1/6 🧵 The videos below are fully narrated so make sure to turn on the audio 🔊 Yes, you'll need a subscription on both Freepik and Pikaframes if you want to create something like this, I would rather be honest and tell you from the start 👍

Yup I'm now 100% convinced that @midjourney Video has thee best video model for retaining style/aesthetics while adding motion. It also has the most seamless extend feature out of every other video model on the market, it's completely seamless, no other platform can even compare to Midjourney's extend. I don't know what magic they're doing behind the scenes to create the best extend I've ever used. Usually when you extend videos you have a jarring indication when an extension happens and an extension can even cause the style to gradually change. It can also alter the speed of motion or blow out highlights in a video. With Midjourney Video you don't notice it at all! It's crazy! The second video of the man experiencing a braindance with wires connected to his brain is utilizing a Midjourey extend.

I created an arcade machine with #Blender & #Eevee to relive some of my childhood memories. This is part of a much bigger scene, i'm trying to build an entire arcade store. I also wanted to fuse 2D and 3D by using video elements within a real time 3D viewport. #3D

Currently testing @TencentHunyuan brand new 2.5 model for image to 3D. YUP! It's MAJOR improvement over 2.0, especially with making details look sharper, it can also reconstruct more detail. It also generates PBR materials now and you can automatically rig the character on the website. It's much better than Trellis and Tripo from my testing! Took it into Blender as well to compare Hunyuan 2.5 (on the left) and Hunyuan 2.0 (on the right). I wanted to see the mesh with a solid and material preview. If you're doing 3D printing, these would probably work very well. However...the biggest issue here is still topology which is a complete and utter mess, there's also still issues with texture projection...and the entire model is a single mesh, there needs to be a method to generate the model in parts BUT this tech is certainly improving. As someone that is also a 3D artist, I actually want to see what this tech is capable of generating to output 3D models.

Quick tip for anyone using multi image reference with Flux Kontext. If you have someone holding a product, you need to specify how big the product needs to be so that it looks accurate in their hand/s. By default the products appear massive from what I've noticed (unless you intentionally want the product to look huge). Incorrect Prompt: The man is holding an energy drink can in his right hand Optimized Prompt: The man is holding a small size energy drink can in his right hand A small size can to me still looks medium so if I wanted it even smaller maybe I can say very small can in the prompt. P.S I'm using multi image reference via @freepik

Decided to give #Embergen another try for fire simulations. It's obviously still super amazing. Rendered this scene in #Cinema4D & #OctaneRender and used some #Megascan assets for the landscape. I'm exploring workflows to use these Embergen VDB's properly with Octane Render. #3D

This is BLITZ 🏍️ starring myself. I've tested a workflow that combines two of the best AI image editing models right now, Nano Banana and Seedream 4. Using these together feels like a superpower. Seedream 4 for instance generates much more dynamic camera angles BUT Nano Banana does a better job with overall consistency, so utilizing both is super beneficial. I wanted to create a sequence where I'm riding a Cyberbike with an electric booster that overclocks the motor to deliver short, high-risk bursts of extreme speed. The location is a white sand desert. I decided to also test @Hailuo_AI start and end frame feature which in my opinion is one of the best since it understands so much about context and camera movement. Start and ends frames let you have much better control over camera movement but where Hailuo truly excels is that it understands speed and camera shake which are essential for any fast paced action sequences. The music was generated with Suno 4.5+ and some additional sound effects like the bike and wind in the desert were sourced from Artlist. Edited with Capcut. There's some more tips and tricks in the thread 👍👍

JEALOUSY - What happens when an AI Artist Robot experiences human emotion? 🩸🩸🩸 My new True Crime Fiction AI short film. Tools used for it's production: Image Generation - Flux (Generated locally) Image Upscaler - @Magnific_AI Image To Video - @Hailuo_AI Voiceover - @elevenlabsio (And Myself) Lip sync - @HeyGen_Official Video Editing - @capcutapp Music & Sound Effects - Elevenlabs and @Artlist_io Additional Foley - Recorded on my iPhone Story co-created with @AnthropicAI Claude You can also watch it on youtube in upscaled 4K resolution youtube.com/watch?v=zLTS6q… JEALOUSY was created with the intent to see what is currently possible with a variety of AI tools. This is an entire story with consistent characters, music, sound effects, lip syncing and voiceovers. Let me know what you think 👍

I created a burger commercial using AI. Introducing THE SCORCHER! The Worlds hottest burger! Images created with @freepik MYSTIC and brought to life with @LumaLabsAI. Logos created with @ideogram_ai Music generated with @udiomusic and narration by @elevenlabsio

I've had early access to @Kling_ai brand new 2.0 video model and done extensive testing and trust me when I say that this model upgrade is AMAZING!!! 🔥 The amount of incredible dynamic action that you can generate now is next level. If you want to make things go fast, the new model completely excels at this, movement looks very natural and fluid. This is a major release for Kling! Here is a collection of some clips I've generated with the 2.0 model.

Yup I'm now 100% convinced that @midjourney Video has thee best video model for retaining style/aesthetics while adding motion. It also has the most seamless extend feature out of every other video model on the market, it's completely seamless, no other platform can even compare to Midjourney's extend. I don't know what magic they're doing behind the scenes to create the best extend I've ever used. Usually when you extend videos you have a jarring indication when an extension happens and an extension can even cause the style to gradually change. It can also alter the speed of motion or blow out highlights in a video. With Midjourney Video you don't notice it at all! It's crazy! The second video of the man experiencing a braindance with wires connected to his brain is utilizing a Midjourey extend.

I'm officially a @Hailuo_AI Creative Partner! I'm extremely grateful for this opportunity. I can't wait to bring more crazy ideas in my head to life. Thank you Hailuo for believing in me to utilize your tools. Let's bring some stories to life :) 🙏👍❤️🧡💛💙 #AI #Hailuo

It's spooky season🐺 I always wanted to try and do a werewolf transformation. I'm early testing @Hailuo_AI 2.3 and yes, in terms of cinematic outputs, I'm still loving it! What I really love about Hailuo is how it understands camera prompting instructions, it's very good! It looks like the new update makes prompt adherence even better. Shoutout to @Uncanny_Harry for the inspiration regarding transformations.

PSYCHOSIS - My first AI Horror Short - A woman describes the manifestation of her own mind during a 911 call. - Images generated locally with Flux - Text/Image To Video - @Hailuo_AI - Audio & Sound Effects - @elevenlabsio & ChatGPT Voice - Music - @udiomusic #AI #AIVideo