Uncensored Wan 1.3B fine-tune hits Hugging Face, runs video gen on 8GB VRAM
Promptmethus · x · 2026-10-27
An uncensored fine-tune of Wan 1.3B (wan1.3Bexpe14) is now on Hugging Face, pitched as free text-to-video with no built-in filter.
- 2.8GB file; base model needs 8GB VRAM, so consumer gaming GPUs can run it
- Drops into ComfyUI's existing Wan 2.1 workflow
- Generates short 480p clips from prompts
The post also plugs Chroma1-HD, another uncensored open model (8.9B, Apache 2.0, 5.57GB Q4) that runs offline locally. Fully unguarded lightweight open models keep spreading fast in the local-deployment scene.
More from Models
- Doctor's Prescription OCR Test: Gemma 4 31B Now Reads What Models Couldn't a Year Ago — MaziyarPanahi · 2026-10-27
- cyb3rops: open-weight AI models mean attackers can compromise 90% of orgs without new exploits — cyb3rops · 2026-10-27
- Study Finds GPT-6 Astra Only Partially Capable at CAD Workflows — ZhejiangUniversity · 2026-10-27
- Anthropic investigates elevated error rates for Claude Sonnet 5.5 — ClaudeAI-mod-bot · 2026-10-27
- GPT-6.1-Terra hits #2 on EyeBench but burns 2.4x tokens, costing more than Sol — adonis_singh · 2026-10-27
- Claude Opus 5.5 safeguards flagged as flagging normal dev work, users grumble — philipvollet · 2026-10-27