1:28Our newest AI Short Film “PAPER JAM”! Each keyframe was animated by hand based on AI generated 3D models. "Rendered" using Flux + regional Loras in ComfyUI and interpolated using @Kling_aiMMickmumpitz2.4MX
0:061:1point and click ⬅️ Made in @ComfyUI + @Photoshop + @AdobeAE with GPT Image 2.0 and Wan 2.2 I2V ✏️🤖IEIngi Erlingsson 🪄271KX
0:40I love open source AI in @ComfyUI because it lets me control every step. For this spaceship shot I tracked the camera, designed layout geometry in Blender, exported depth maps, prompted the final look with an AI image editor, and jumped into Photoshop to clean it all up.MMickmumpitz48.1KX
0:071:1SapienOS™ Made in @ComfyUI with GPT Image 2.0, Wan 2.2 I2V + vace, @thesystms HUD, Florence2, Sapiens2 + @sunoIEIngi Erlingsson 🪄27.1KX
0:051:1Spaced latents 🪐 Made in @ComfyUI with Wan 2.2 I2V + Vace, GPT Image 2.0 and a time slicing node I've been working onIEIngi Erlingsson 🪄26.3KX
0:121:1[build]⛏️[/rebuild] over the past year I've been working on a set of LoRAs for seamless transitions and now that they're starting to click I'm experimenting with ways of integrating performance Made in @ComfyUI with @krea_ai 2 / GPT Image 2.0 / Wan 2.2 / @thesystms HUD @sunoIEIngi Erlingsson 🪄25.2KX
0:071:1Task successfully failed ✅ Made in @ComfyUI and @AdobeAE with Wan 2.2 I2V, @krea_ai Image 2 + @thesystms TimeSlice nodes ✂️ + @sunoIEIngi Erlingsson 🪄15.3KX
0:101:1inner monologue 💭 testing out some new transition ideas.. made in @ComfyUI and @AdobeAE with GPT Image 2.0 + Wan 2.2 I2V/T2V/Vace and @suno 🎵IEIngi Erlingsson 🪄13KX
0:48Workflow experiment. Flux Lora -> Various images in ComfyUI -> Animate in RunwayML -> Make a video with iPhone -> Animate videoclips with Live Portrait to get lipsync and facial expressions :D @runwaymlAKAntti Karppinen 🎨1.1KX
0:58Example workflow for making your characters move and talk. Midjourney+Luma.ai+Elevenlabs+ComfyUI (liveportrait video2video) Getting better every day, and more control is always better! @midjourney @LumaLabsAI @elevenlabsAKAntti Karppinen 🎨878X
0:159:16A fun way to get some more control from your AI outputs. It uses an open source model called SAM 3D body for the motion capture that get transferred into Blender. From there I create camera motions and then run it through Seedance 2.5.ESEric Solorio605Threads
0:199:16Using some household stuff to inpaint some sci-fi gear using Minimax H3. This was ran locally on my PC.ESEric Solorio21Threads
0:109:16Trying my hand at redoing this scene from the first Terminator movie. They were probably limited by both the budget and the technology available at the time, though they of course refined it in the sequel. What I love is that even with the stiff robotic movement, it actually feels appropriate, it maESEric Solorio622Threads
0:399:16Breakfast is served 🧑🍳 Made with: Nano Banana Pro Wan 2.2 Animate Kling 2.5 First and Last FrameESEric Solorio130Threads