Zuntan
/

Wan21-FastMix

Model card Files Files and versions

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Wan 2.1 I2V, 4 steps / generation. Both 480p and 720p LoRA are available.

2025/07/26

Wan21-BothI2v-FastMix2-14B: Basic model.
- Wan21-BothI2v-FastPusaMix2-14B: Pusa merged.
Wan21-BothI2vAnisora-FastMix2-14B: Anisora merged. Reduces the realistic appearance of the face.
- Wan21-BothI2vAnisora-FastPusaMix2-14B: Pusa merged.

Wan21-BothI2v-FastMix2-14B

Q3_K_M, Scheduler: lcm, Step: 4, Cfg: 1, Shift: 8, base_precision: fp16_fast, Use compile & block_swap
HiresFix: Latent x1.5 bicubic, Denoise 0.45, Scheduler: lcm, Step: 3, Cfg: 1, Shift: 12, base_precision: fp16_fast, Use compile & block_swap

Wan21-BothI2v-FastPusaMix2-14B

Q3_K_M, Scheduler: flowmatch_pusa, Step: 4, Cfg: 1, Shift: 8, base_precision: fp16_fast, Use compile & block_swap
HiresFix: Latent x1.5 bicubic, Denoise 0.45, Scheduler: lcm, Step: 3, Cfg: 1, Shift: 12, base_precision: fp16_fast, Use compile & block_swap

Wan21-BothI2vAnisora-FastMix2-14B

Q3_K_M, Scheduler: lcm, Step: 4, Cfg: 1, Shift: 8, base_precision: fp16_fast, Use compile & block_swap
HiresFix: Latent x1.5 bicubic, Denoise 0.45, Scheduler: lcm, Step: 3, Cfg: 1, Shift: 12, base_precision: fp16_fast, Use compile & block_swap

Wan21-BothI2vAnisora-FastPusaMix2-14B

Q3_K_M, Scheduler: flowmatch_pusa, Step: 4, Cfg: 1, Shift: 8, base_precision: fp16_fast, Use compile & block_swap
HiresFix: Latent x1.5 bicubic, Denoise 0.45, Scheduler: lcm, Step: 3, Cfg: 1, Shift: 12, base_precision: fp16_fast, Use compile & block_swap

Wan21-I2V-14B

Wan21-BothI2vAnisora-14B

Wan21-BothI2v-14B-FastMix

Scheduler: lcm, Step: 4, Cfg: 1, Shift: 8, base_precision: fp16_fast, Use compile & block_swap, EnhanceA(weight: 1, start: 0, end: 0)

Hires. fix

Latent x1.5 bicubic, Denoise 0.3, Scheduler: lcm, Step: 4, Cfg: 1, Shift: 12, base_precision: fp16_fast, Use compile & block_swap

Wan21-VACE-14B-FastMix

Scheduler: unipc, Step: 4, Cfg: 1, Shift: 8, base_precision: fp16_fast, Use compile & block_swap

I2v-WanSkyRel07-14B-480p

I2v-WanSkyRel07-14B-720p

I2v-WanSkyRel07-14B

Downloads last month: 3,152

GGUF

Model size

16B params

Architecture

wan

Hardware compatibility

Log In to view the estimation

3-bit

4-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support