<div data-youtube-video="https://youtu.be/R3W2ab1_TzY"><iframe src="https://www.youtube.com/embed/R3W2ab1_TzY" width="853" height="480" allowfullscreen></iframe></div> 
 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2098775640674054145?inviteCode=rh-v1111Bilibili tutorial video: https://www.bilibili.com/video/BV1vFYz6HECU/# SelfLift — 768P-labelled preset## Purpose and preparationResolve the matching custom-node/runtime versions and assets. Load authorized media and inspect active inputs, actual schedules, effective dimensions and every save destination before a small test.One active reference, image 150 at slot 0; no second image loader.The generation selector requests 16:9,1.03MP,multiple32; links override cached1344×768. Duration 5 feeds the alignment expression, requesting124 frames, nominal about 5.167 seconds at 24fps. Exact raster and duration remain unverified.The active LightX2V LoRA is named 4step and has strength about 0.65, but BasicScheduler stores simple/8/denoise1 before H3SigmaRefiner(extra_steps 1,start 0.7,end 0,cosine). Do not present this as a measured four-step run or infer total NFE. LowVRAMAttention and ChunkFeedForward nodes are bypassed.SelfLift stores CFG 1,transition 6,lowres_scale 0.4,rho 0,w_min 0.5,w_max 1,BF16 learned latent upscaler and highres_tiling=false. Negative conditioning is ZeroOut. Preview 1024/12fps is not export resolution/FPS. Native generated audio feeds assembly/interpolation; source drive/final/reference-audio ports are unconnected and conditioner mux_audio is unused.No SeedVR2 or fixed-raster resize tail is present. Do not borrow a larger variant's processing chain. SelfLift still uses learned latent processing internally.Interpolation requests 2x,motion auto,threshold0.24,keep_audio on. This is temporal, not spatial scaling. For generation presets,24→48fps is configured intent, not measured cadence/frame count/duration. Combined VIDEO and explicit images/audio are connected; precedence requires implementation review. VIDEO output feeds SaveVideo with auto format/codec.## Files and selected assets- [Workflow JSON]()- [Selected cover]()- `minimax_h3_hybrid_fl2va_ref2va_b25-49-int8.safetensors`- `qwen3vl_32b_minimax_h3_int8_convrot.safetensors`- `minimax_h3_audio_vae_fp32.safetensors`- `minimax_h3_video_vae_fp16.safetensors`- `minimax_h3_fl2v_lightx2v_turbo_4step_v0.1_comfy.safetensors`- `minimax_h3_latent_upscaler_3d_bf16.safetensors`- `taeh3.safetensors`## Version, evidence and rightsThis is a local descriptive draft, not a published upgrade. Files01–08 are byte-identical to originals; only the standalone ninth file's historical video-preview field is cleared in its new copy. Originals remain unchanged.No model inference, visual/audio acceptance, wall-clock benchmark or license verification was performed. Covers are selected assets, not accepted render evidence. Weights and external input media are not bundled. Check workflow, nodes, models, LoRAs, source media and cover rights separately; no blanket commercial license is asserted.[Source-provided tutorial](https://www.youtube.com/watch?v=R3W2ab1_TzY) · [Source-provided workflow entry](https://www.runninghub.cn/post/2098689834578698241/?inviteCode=rh-v1111)Links are not live-verified. The workflow is supplied through AI-KSK.

MiniMax H3 SelfLift Universal Video Generation 768P

<div data-youtube-video="https://youtu.be/R3W2ab1_TzY"></div> 
 
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2098775640674054145?inviteCode=rh-v1111Bilibili tutorial video: https://www.bilibili.com/video/BV1vFYz6HECU/# SelfLift — 768P-labelled preset## Purpose and preparationResolve the matching custom-node/runtime versions and assets. Load authorized media and inspect active inputs, actual schedules, effective dimensions and every save destination before a small test.One active reference, image 150 at slot 0; no second image loader.The generation selector requests 16:9,1.03MP,multiple32; links override cached1344×768. Duration 5 feeds the alignment expression, requesting124 frames, nominal about 5.167 seconds at 24fps. Exact raster and duration remain unverified.The active LightX2V LoRA is named 4step and has strength about 0.65, but BasicScheduler stores simple/8/denoise1 before H3SigmaRefiner(extra_steps 1,start 0.7,end 0,cosine). Do not present this as a measured four-step run or infer total NFE. LowVRAMAttention and ChunkFeedForward nodes are bypassed.SelfLift stores CFG 1,transition 6,lowres_scale 0.4,rho 0,w_min 0.5,w_max 1,BF16 learned latent upscaler and highres_tiling=false. Negative conditioning is ZeroOut. Preview 1024/12fps is not export resolution/FPS. Native generated audio feeds assembly/interpolation; source drive/final/reference-audio ports are unconnected and conditioner mux_audio is unused.No SeedVR2 or fixed-raster resize tail is present. Do not borrow a larger variant's processing chain. SelfLift still uses learned latent processing internally.Interpolation requests 2x,motion auto,threshold0.24,keep_audio on. This is temporal, not spatial scaling. For generation presets,24→48fps is configured intent, not measured cadence/frame count/duration. Combined VIDEO and explicit images/audio are connected; precedence requires implementation review. VIDEO output feeds SaveVideo with auto format/codec.## Files and selected assets- [Workflow JSON]()- [Selected cover]()- `minimax_h3_hybrid_fl2va_ref2va_b25-49-int8.safetensors`- `qwen3vl_32b_minimax_h3_int8_convrot.safetensors`- `minimax_h3_audio_vae_fp32.safetensors`- `minimax_h3_video_vae_fp16.safetensors`- `minimax_h3_fl2v_lightx2v_turbo_4step_v0.1_comfy.safetensors`- `minimax_h3_latent_upscaler_3d_bf16.safetensors`- `taeh3.safetensors`## Version, evidence and rightsThis is a local descriptive draft, not a published upgrade. Files01–08 are byte-identical to originals; only the standalone ninth file's historical video-preview field is cleared in its new copy. Originals remain unchanged.No model inference, visual/audio acceptance, wall-clock benchmark or license verification was performed. Covers are selected assets, not accepted render evidence. Weights and external input media are not bundled. Check workflow, nodes, models, LoRAs, source media and cover rights separately; no blanket commercial license is asserted.[Source-provided tutorial](https://www.youtube.com/watch?v=R3W2ab1_TzY) · [Source-provided workflow entry](https://www.runninghub.cn/post/2098689834578698241/?inviteCode=rh-v1111)Links are not live-verified. The workflow is supplied through AI-KSK.

minimaxH3Selflift_v10.json

v1.0

<div data-youtube-video="https://youtu.be/R3W2ab1_TzY"><iframe src="https://www.youtube.com/embed/R3W2ab1_TzY" width="853" height="480" allowfullscreen></iframe></div> 
 
AI-KSK ComfyUI workflow: MiniMax H3 SelfLift 768P Fast Preview. The fastest path of the 9-workflow MiniMax H3 pack, built for quick prompt iteration before committing to high-resolution finals. 
 
Main features: 
- MiniMax H3 hybrid FL2VA/Ref2VA INT8 UNET with Qwen3-VL 32B text encoder, video and audio VAEs for native audio generation. 
- SelfLift 3D latent refinement with the MiniMax H3 latent upscaler and FL2V Turbo 4-step LoRA at 0.65 strength, 8-step Euler sampling. 
- 1.03 MP 16:9 base generation with native audio, no post upscaling, so previews render in a single pass. 
- DLSS 2x frame interpolation on the final output (24 to 48 FPS). 
- Use this tier to check prompt, motion, and audio before moving the same setup to 2K or 4K finals. 
 
Suggested workflow: 
1. Import the JSON into ComfyUI and install the model files and custom nodes referenced by the workflow. 
2. Provide the required text, image, or video inputs for the selected path. 
3. Adjust resolution, steps, denoise, and prompt controls, then run the connected SaveVideo output. 
 
 
RunningHub workflow: 
https://www.runninghub.ai/zh-cn/post/2098775640674054145?inviteCode=rh-v1111 
 
AI-KSK RunningHub workflow hub: 
https://www.runninghub.ai/user-center/1892566146468511746?inviteCode=rh-v1111 
 
Bilibili tutorial: 
https://www.bilibili.com/video/BV1vFYz6HECU/ 
 
RunningHub registration and AI tools: 
https://www.runninghub.ai/?inviteCode=rh-v1111 
https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111 
https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111 
https://rhtv.runninghub.ai/projects?inviteCode=rh-v1111 
 
Stable global access: 
https://lelians.com/#/register?code=mFIJ5tZn 
 
TokenRhythm AI model credits: 
https://tokenrhythm.studio/i/rf_tr_kM6wekDquDDZQD4PUNmgiuHA 
 
Youyun Cloud GPU: 
https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq 
https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52 
 
RunPod Cloud GPU: 
https://runpod.io/?ref=sxk5n5m7 
 
Support AI-KSK: 
https://ko-fi.com/aiksk

MiniMax H3 SelfLift 768P Fast Preview

<div data-youtube-video="https://youtu.be/R3W2ab1_TzY"></div> 
 
AI-KSK ComfyUI workflow: MiniMax H3 SelfLift 768P Fast Preview. The fastest path of the 9-workflow MiniMax H3 pack, built for quick prompt iteration before committing to high-resolution finals. 
 
Main features: 
- MiniMax H3 hybrid FL2VA/Ref2VA INT8 UNET with Qwen3-VL 32B text encoder, video and audio VAEs for native audio generation. 
- SelfLift 3D latent refinement with the MiniMax H3 latent upscaler and FL2V Turbo 4-step LoRA at 0.65 strength, 8-step Euler sampling. 
- 1.03 MP 16:9 base generation with native audio, no post upscaling, so previews render in a single pass. 
- DLSS 2x frame interpolation on the final output (24 to 48 FPS). 
- Use this tier to check prompt, motion, and audio before moving the same setup to 2K or 4K finals. 
 
Suggested workflow: 
1. Import the JSON into ComfyUI and install the model files and custom nodes referenced by the workflow. 
2. Provide the required text, image, or video inputs for the selected path. 
3. Adjust resolution, steps, denoise, and prompt controls, then run the connected SaveVideo output. 
 
 
RunningHub workflow: 
https://www.runninghub.ai/zh-cn/post/2098775640674054145?inviteCode=rh-v1111 
 
AI-KSK RunningHub workflow hub: 
https://www.runninghub.ai/user-center/1892566146468511746?inviteCode=rh-v1111 
 
Bilibili tutorial: 
https://www.bilibili.com/video/BV1vFYz6HECU/ 
 
RunningHub registration and AI tools: 
https://www.runninghub.ai/?inviteCode=rh-v1111 
https://www.runninghub.ai/ai-generator/2046514150500524034?inviteCode=rh-v1111 
https://www.runninghub.ai/vip-rights/3?inviteCode=rh-v1111 
https://rhtv.runninghub.ai/projects?inviteCode=rh-v1111 
 
Stable global access: 
https://lelians.com/#/register?code=mFIJ5tZn 
 
TokenRhythm AI model credits: 
https://tokenrhythm.studio/i/rf_tr_kM6wekDquDDZQD4PUNmgiuHA 
 
Youyun Cloud GPU: 
https://passport.compshare.cn/register?referral_code=A7fTQUYY9lCDFJwA6MMvoq 
https://www.notion.so/2b72459a3ac6808f8282f2c687ed8f52 
 
RunPod Cloud GPU: 
https://runpod.io/?ref=sxk5n5m7 
 
Support AI-KSK: 
https://ko-fi.com/aiksk

Files with SHA256: f37a4b260ebe9676d9b91b24351751cb11949cee5abab0b6d7fa72e548f3140c