Drama 3 for ComfyUI β fp8 experts, bf16 dense
A conversion of fishaudio/drama-3 for the ComfyUI-Drama3 node pack.
- Copied from: https://huggingface.co/fishaudio/drama-3 β revision
78e5ab79e49a, the weights uploaded 2026-10-29 (15 shards; the earlier 8-shard files were removed upstream that day). - Script used:
tools/convert.pyfrom https://github.com/PedroMarinhoDev/ComfyUI-Drama3python tools/convert.py model <drama-3 folder> drama3_fp8experts_bf16.safetensors --format fp8 - What is in the file: the routed experts are the checkpoint's own block-FP8 tensors (128x128 scales) copied byte for byte; every other linear keeps the checkpoint's bf16. Gate/up projections are fused; the LM head is trimmed to the rows generation samples from (1 end-of-speech + 4096 semantic tokens).
- How to use: put the file in
ComfyUI/models/diffusion_models/and load it with theDrama3Loadernode. Pair it withdrama3_codec.safetensorsinComfyUI/models/vae/and Qwen3-ASR inComfyUI/models/asr/(both from the pack's own Hub repos). - File:
drama3_fp8experts_bf16.safetensorsβ 38,578,417,928 bytes, 912 tensors, sha256cfd27b526b35a66729ffd1d6966bf13f7856f4c59f917497eaded6ecb0b888de.
Note: the prebuilt file in PedroMarinhoDev/Drama-3-ComfyUI comes from an earlier revision of the base model. This file matches the 2026-10-29 weights, and its tensors were verified byte-identical to that checkpoint.
License: Fish Audio's (see the fishaudio/drama-3 model card and the license file in this repo).
Model tree for zzb1420/Drama-3-ComfyUI
Base model
fishaudio/drama-3