Proficient in graphical model training and dataset design. Also for ComfyUI node creation and advanced workflow customization.

shang hai
Joined June 2010
Made a live-action-style recreation of Haruhi’s “God knows…” for the anime’s 20th anniversary. Matched the shots, timing, and lip sync to the original. Still love this song and the whole SOS Brigade. Especially Kyon. Made with AI and a lot of frame-by-frame tweaking. #涼宮ハルヒの憂鬱 #Godknows
2
3
6
687
Slayers NEXT OP, reimagined in live action 🔥 Lina’s opening line made me tear up while editing. My friends and I once filmed Lina skits in a park with a camcorder. I can’t find the tapes now, but I still remember the joy. Welcome back, Lina. #Slayers #LinaInverse #minimax
201
「ねえ、私って可愛い?」🥺 “Am I cute?” She got closer to make sure the answer was YES. 👀✨ One image. Ten seconds. Cuteness overload. Made with MiniMax H3. #MiniMaxH3 #AIvideo #Anime
1
719
What if your food could… un-cook itself? 👀🎧 A little reverse-cooking ASMR experiment. One tap — and a finished dish slowly returns to its original ingredients. No cuts. No magic smoke. Just every ingredient finding its way back. This Meal Was Made for Nothing. #01 — Soufflé 🥞 Headphones recommended 🎧 #ASMR #Satisfying #AIVideo #GenerativeAI #FoodASMR #ReverseCooking #AIArt
117
One Template, Many Worlds | A Cinematic AI Experiment build with the white model from createwithclint render by Minimax H3 to 5K high resolution just let me know which world you like. #minimax #openai #createwithclint
🤖 Made with AI
212
GPT-image-2.5根本难不倒!anything it can draw #openai #chatgpt
2
260
TTPlanet retweeted
ChatGPT Images 2.5—faster, sharper, smarter, with better tools for creating whatever you can dream of. - Faster image generation to keep your ideas flowing - Improved fidelity for more natural, recognizable images - Consistent details across multiple edits - Comment-based edits to change only what you want
938
2,559
1,882
23,682
8,163,454
Years ago, I trained a model to generate miniature cities. This was one of its images. Never imagined I’d turn it into a 3D scene in Blender—streetlights, grass, underground canals and all. A city I could only look at is now one I can explore.#openai #blender #miniature
1
4
255
I know GPT-6 is strong, but it deliver the result like this with ultra mode!:)#gpt-astra #openai #gpt-6
248
The live-action Tekkaman Blade OP (1992)we never got—remake shot by shot. ⚡ As a kid, Tekkaman Blade meant armor and battles. Now I understand its tragedy: losing everything—and fighting on. Custom SFX inspired by JoJo’s special-episode OPs. The original anime runs in sync. SOUND ON. 🔊 Built end-to-end with MiniMax H3, ComfyUI & GPT. @MiniMax_AI @ComfyUI @OpenAI #ComfyH3 #TekkamanBlade
1
2
8
663
Minimax H3 Max has generates video faster than you can watch it so I hooked it to a twitch livestream! Now you can watch infinite interdimensional cable - link to the stream below
625
1,035
813
13,366
6,182,107
My original MV “Silver” follows virtual idol Linae as she journeys through five worlds—before fading into a sea of silver. Created using MiniMax H3 and ComfyUI. @comfyUI @minimax #ComfyH3 #AIMV #VirtualIdol #AIAnimation
1
3
945
Smart Tile 2.0 is now the main feature of ComfyUI TTP Toolset. This update turns tiled upscaling into a much more controllable image editing workflow: github.com/TTPlanetPig/Comfy… Visual tile editor Mask-to-tile replacement Manual + Auto Tile layout Object-aware variable-size tiles Per-tile img2img loop Mask-aware assembly Detail-focused upscale Instead of cutting every image into equal squares, Smart Tile lets you build tiles around the actual visual structure: face, eyes, hands, text, clothing, foreground details, subject, and background. For AI image creators, this means more control over where details are enhanced, where the image should stay stable, and how the final high-resolution result is assembled. GitHub: TTPlanetPig / Comfyui_TTP_Toolset #ComfyUI #AIArt #StableDiffusion #Flux #ImageUpscaling #SmartTile #TTPToolset
1
1
367
I did not post a lot of seeddance 2.0 sample but here is some. ep1 and ep2 are same consistent character. ep3 is build with 2 individual photo. #danceseed2 @dreamina_ai
1
4
2,139
Comfyui support for DreamID-V,if you like my node remember to click the star:) original github:github.com/bytedance/DreamID… comfyui node:github.com/TTPlanetPig/Comfy… #comfyui #bytedance #AIvideo #faceswap
1
349
Update the TTP_tooset for comfyui. It will bring you a new node to support NEW LTX 2 first and last frame control capability. Workflow are in the sample folder github.com/TTPlanetPig/Comfy…
7
2
39
15,727
Mecha Virtual Idol Debut Single — "Binary Breath": The Aesthetic of Blue & White Violence. Body: "Cold logic, warm longing." What started as a small experiment into the boundaries of AI in 2025 evolved into my first full-scale Music Video. As LINAE emerged from the blue and white code, I became captivated by the friction between her heavy armor and her delicate soul. About LINAE: "Lin (泠)" stands for the cold, transparent void. "Nae (奈)" represents the resolute yet tender vitality of a girl. She isn't just a 2D illustration; she is stepping into the weight of the real world. The Craft: To avoid the "plastic 3D" look common in AI, I spent weeks fine-tuning custom LoRAs and merging cutting-edge models to achieve that raw contrast between metallic structures and biological skin. This is LINAE’s first breath—and my awakening alongside AI. AI Tech Stack: 🛠️ Google Gemini Pro 🛠️ Jimeng (Dreamina) 3.5 Pro 🛠️ Wan 2.1 Series 🛠️ Qwen-edit 🛠️ Suno AI 🛠️ Flux + Custom Trained LoRAs #LINAE #VirtualIdol #AIArt #Cyberpunk #Mecha #GenerativeAI #MusicVideo
1
261
Gundam Girl outshape design! NOW it with great consistency and realistic photo #gundam #mechagirl #RX78
1
238