TTPlanet

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

[TTPlanet @ttplanet]

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

[TTPlanet @ttplanet]

Comfyui support for DreamID-V，if you like my node remember to click the star：）
original github：https://t.co/9iI5bH8SNj
comfyui node：https://t.co/sC3qOSLNHE
#comfyui #bytedance #AIvideo #faceswap

[TTPlanet @ttplanet]

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

https://t.co/Cfue7RDAbL

[TTPlanet @ttplanet]

Mecha Virtual Idol <LINAE-泠奈> 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

[TTPlanet @ttplanet]

Gundam Girl outshape design！
NOW it with great consistency and realistic photo
#gundam
#mechagirl
#RX78

[TTPlanet @ttplanet]

@love_deepseek @Alibaba_Wan online wan2.2 gen with auto music

[TTPlanet @ttplanet]

Wan2.2 The quality is significantly improved, tested some human body performance. Amazing
@Alibaba_Wan #wan2.2

[TTPlanet @ttplanet]

I didi not realize it could be used in this way

[Daxiong (Lin) @ComfyUIWiki]

I'm having fun with @ttplanet's Kontext PVC LoRA today. It's not a public LoRA, so I'm not able to share it with everyone

[TTPlanet @ttplanet]

Step1, Pick up a photo you like
Step2, Use my PVC Lora for FBL Kontext to convert to image to a high quality figure preview image
Step3, Use Tencent Hunyuan 3D model to convert single image to a functional 3D model
Step4, Print it, if you can use SLA rather than FDM, you will get much better Surface! @TencentHunyuan @bfl_ml

[TTPlanet @ttplanet]

Kontext PVC lora-real convertion for the realistic photo or comic characters. Super high quality and consistence for output. However, not for free this time as training collection is with very high effort.
If you want it, contact me by qq group: 1050777195 or tg group: https://t.co/tpg3e1Dg0A

[TTPlanet @ttplanet]

@angrypenguinPNG could you share how you set the promot to move the camera？my video stay solid with same background！ Thanks

[TTPlanet @ttplanet]

Thanks KJ for re-build the logic for multitalk in Comfyui
now it work fine and amazing
@Kijaidesign

[TTPlanet @ttplanet]

Hunyuan 3D 2.5 look much better

[Tencent Hy @TencentHunyuan]

Some friends mentioned they couldn’t recreate the cases we shared.
No worries!😊 We’ve got you covered with direct links from our platform below.
Click on each case to view and download the input images. You can also explore the models in various modes like texture, wireframe, albedo, or normal maps. We hope you enjoy them and find them inspiring!

Angel: https://t.co/SFgsV6Vonx

Chinese Ancient Architecture: https://t.co/avOnwxviFo

Bridge: https://t.co/H7wTIuOKyu

Robot: https://t.co/Vba7aCDonO

Feel free to share your thoughts or creations with us! #3DModeling #AI #hunyuan3d

[TTPlanet @ttplanet]

Now I put my Modified Start End FramePack logic from my original PR https://t.co/LzKCEi4cs2 into comfyui node, I have improved the variability significantly by adjusting the end frame strength and history latent reference. Please use 8s/0.8 end image strength and 0.1 history decay to get better result.

https://t.co/2AQTH1Fwtc

KJ maybe you can check how to optimize the way to allocate the strength control
@Kijaidesign

[TTPlanet @ttplanet]

Again Framepack start to end。8s。my felling it is better than close source application. smooth and logical！
#FramePack

[TTPlanet @ttplanet]

Made some experimental again today on frame pack code, now more variable on the start to end frame version.
@lvminzhang @TencentHunyuan #FramePack #HunyuanVideo

Again Rem 赛高

[TTPlanet @ttplanet]

@OverPowere13959 @lvminzhang @TencentHunyuan sure,please refer to https://t.co/yUI7s3zl2l

[TTPlanet @ttplanet]

Just modified @lvminzhang 's framepack and add the start and end frame control!!!! now it can create wonderfull video based on your willingness!!!
I have proposed a PR and waiting for approval.
the effect as belows: you can decide if you want fast or slow!
@TencentHunyuan

[TTPlanet @ttplanet]

@Teslanaut @TencentHunyuan maybe latentsync？I will try

[TTPlanet @ttplanet]

Framepack 30s 720P 1s by RTX4090 120s
Very stable quality！ Hunyuan reborn！ @TencentHunyuan