Skip to content

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Anime POV Whisper Pipeline Pack

Self-hosted anime "talking to you" clip generator — ComfyUI + Wan 2.1 I2V + GPT-SoVITS

Generate cozy 9:16 anime POV clips (character whispering to the viewer, JP voice, burned-in JP/TH subs) 100% locally on a 12GB GPU. No subscriptions, no watermarks, no cloud.

What's inside

File Purpose
workflows/wan_i2v_81f_api.json ComfyUI API-format workflow (Wan 2.1 I2V 14B GGUF Q4, 480x832, 81 frames)
scripts/render_i2v_batch.py Queue N characters through ComfyUI REST, poll, verify outputs
scripts/gen_voice_missing.py GPT-SoVITS JP whisper voicegen (idempotent, validates duration+volume)
scripts/finish_batch_overnight.py One-command overnight finisher: frames → speed-match audio → 1080p upscale → burned subs → MP4
templates/subs_jpth.ass Dual-language subtitle style (JP top + TH bottom), ready to edit
README.md This file

Requirements

  • NVIDIA GPU ≥ 12GB VRAM (RTX 3060/4070 class or better), 32GB RAM recommended
  • ComfyUI with: ComfyUI-GGUF nodes
  • Models: wan2.1-i2v-14b-480p-Q4_K_M.gguf, umt5_xxl_fp16.safetensors, clip_vision_h.safetensors, wan_2.1_vae.safetensors (all free on HuggingFace)
  • GPT-SoVITS (RVC-Boss) with a moe/anime voice model
  • ffmpeg, Python 3.11, Pillow

Quick start

  1. Put your character still (full body, 832x1216) into ComfyUI input/
  2. Edit the CHARS list in scripts/render_i2v_batch.py (name, image, motion prompt)
  3. python3 scripts/render_i2v_batch.py — renders queue up automatically
  4. python3 scripts/finish_batch_overnight.py — waits for renders, makes voices, muxes everything into final MP4s with subs
  5. Upload-ready 1080x1872 MP4s come out in renders/

Tips that saved us hours

  • ffmpeg can NOT decode ComfyUI animated WEBP directly — extract frames with PIL (the finisher script already does this)
  • Call ComfyUI /free before starting TTS, or the 12GB card OOMs
  • speed_factor 0.9-0.92 on SoVITS = cozy whisper pacing
  • Fixed seed per line to retry lines that slurred

License

Code: MIT. You keep 100% of your renders — commercial use allowed with models that permit it (check your voice model's license; anime moe voices vary).

About

Generate unlimited anime POV whisper clips 100% locally — ComfyUI + Wan 2.1 I2V + GPT-SoVITS pipeline (12GB GPU)

Topics

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages