YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
π Wan2.1 VACE + Phantom Causvid (Finetune)
Author / Creator: Inner_Reflections_AI
Packaged for WanGP by: hdtrnk
πΉ About This Finetune
This is a custom merge of Wan 2.1 VACE and Phantom, created by Inner_Reflections_AI and purified to FP16 for compatibility with WanGP.
- Architecture:
vace_14B - Mode: Image/Video conditioning with multi-reference support
- Multi-Image: Optimized for 2β4 image references in WanGP custom UI
- Variants: Both FP16 and INT8 versions provided
πΉ Files
- Wan2.1_VACE_Phantom_Causvid_fp16_pure.safetensors
- Wan2.1_VACE_Phantom_Causvid_quanto_bf16_int8_pure.safetensors
πΉ Usage in WanGP
Place the JSON definition file into:
app/finetunes/vace_phantom_causvid.json
Sample finetune entry:
{
"model": {
"name": "VACE Phantom Causvid 14B",
"architecture": "vace_14B",
"description": "VACE-first UI with Phantom multi-image references enabled. Causvid merge, purified FP16 for clean loading & optional INT8 quantization.",
"URLs": [
"https://huggingface.co/hdtrnk/VACEPhantomCausvid/blob/main/Wan2.1_VACE_Phantom_Causvid_fp16_pure.safetensors",
"https://huggingface.co/hdtrnk/VACEPhantomCausvid/blob/main/Wan2.1_VACE_Phantom_Causvid_quanto_bf16_int8_pure.safetensors"
],
"modules": [],
"auto_quantize": false
}
}
πΉ Notes
- This is an experimental finetune. You may need to tweak steps, guidance scale, and reference image setup for best results.
- Works best with multi-image prompts where identities are clearly separated (e.g., βCharacter A on left, Character B on rightβ).
- If you encounter dropdown errors (
Value: on is not in the list...), refresh the UI and reselect options.
πΉ Credits
- Merge & Guide: Inner_Reflections_AI
- Light JSON Packaging & Uploads: hdtrnk
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
π
Ask for provider support