Use the companion LoRA with other quantized models released by FastVideo. Strength 1.0 (extracted deltas from v2).
| File | Link |
|---|---|
| fastvideo_fasth3_trim_8step_bf16_motion_enhanced_v2.safetensors | Download |
| fastvideo_fasth3_trim_8step_bf16_motion_enhanced_v1.safetensors | Download |
LoRA
| File | Link |
|---|---|
| fastvideo_fasth3_trim_8step_companion_LoRA_Comfy.safetensors | Download |
| TaoMate-H3-FL2VA-3Step-FastH3Trim-ComfyUI-BF16.safetensors | Download |
| TaoMate-H3-T2V-3Step-FastH3Trim-ComfyUI-BF16.safetensors | Download |
| 3-Steps (Lora Off -T2V) | 3-Steps T2V | 4-Steps I2V |
|---|---|---|
V2 : About 8% better visuals (8-steps only)
V1: Performs well in I2V scenarios, but visuals suffer in T2V scenarios, especially in full-body shots and at a distance
First Clip: 8-Steps, Second Clip: 4-Steps
8-Steps:
- Sampler: er_sde
- Scheduler: beta
4-Steps (v1):
- Sampler: heun
- Scheduler: sgm_uniform
What's different from the base
- more accurate male and female anatomy
- a better understanding of NSFW-related motion (wan2.2 prompting style)
- Downloads last month
- 292
Model tree for rzgar/FastVideo-FastH3-Trim-Motion-Enhanced-Comfy
Base model
MiniMaxAI/MiniMax-H3 Finetuned
FastVideo/FastVideo-FastH3-8-Step-V2 Finetuned
FastVideo/FastVideo-FastH3-Trim-8-Step