mlx-community
/

Qwen-Image-Flash-bf16

Model card Files Files and versions

Qwen-Image-Flash-bf16

57.7 GB

Ctrl+K

Ctrl+K

1 contributor

History: 10 commits

xocialize's picture

transformer: 20.43B DMD2 4-step DiT bf16 (byte-identical to upstream)

9cf50ab verified about 14 hours ago

scheduler
scheduler: packaged static shift-3 FlowMatchEuler config about 14 hours ago
text_encoder
text_encoder: Qwen2.5-VL-7B (byte-identical to upstream) about 14 hours ago
tokenizer
tokenizer: fast tokenizer.json converted from the upstream slow files (token-id verified) about 14 hours ago
transformer
transformer: 20.43B DMD2 4-step DiT bf16 (byte-identical to upstream) about 14 hours ago
vae
vae: AutoencoderKLQwenImage (byte-identical to upstream) about 14 hours ago
.gitattributes
1.58 kB
tokenizer: fast tokenizer.json converted from the upstream slow files (token-id verified) about 14 hours ago
LICENSE
11.3 kB
LICENSE (Apache-2.0, additional information per upstream) about 14 hours ago
NOTICE
790 Bytes
NOTICE: NVIDIA Open Model License attribution (OML 3.1) about 14 hours ago
README.md
4.13 kB
README: MLX snapshot notes, distillation defaults, license notice about 14 hours ago
model_index.json
443 Bytes
model_index.json about 14 hours ago