drbaph commited on
Commit
b5afd37
·
verified ·
1 Parent(s): 24ea2fb

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -37,6 +37,12 @@ This repository contains third-party ComfyUI compatibility conversions of the or
37
 
38
  These conversions are intended for the **pruned/curve-form MiniMax-H3 checkpoint used by ComfyUI**.
39
 
 
 
 
 
 
 
40
  ## Original Project
41
 
42
  The original LoRA weights, training work, four-step distillation method, dual video/audio sampling implementation, documentation and source files were created and released by **larryvrh**:
@@ -54,6 +60,9 @@ Full credit for the original MiniMax-H3 Turbo LoRA belongs to **larryvrh**.
54
  |---|---|
55
  | `minimax_h3_turbo_4step_pruned_comfyui.safetensors` | Partial ComfyUI compatibility conversion of the original trained non-EMA weights for the pruned/curve-form MiniMax-H3 checkpoint. The original author describes these weights as crisper and better at holding fast motion. |
56
  | `minimax_h3_turbo_4step_ema_pruned_comfyui.safetensors` | Partial ComfyUI compatibility conversion of the time-averaged EMA weights for the pruned/curve-form MiniMax-H3 checkpoint. The original author describes this early EMA checkpoint as smoother but softer and not yet fully matured. |
 
 
 
57
 
58
  The EMA and non-EMA files remain separate and contain different tensor values.
59
 
 
37
 
38
  These conversions are intended for the **pruned/curve-form MiniMax-H3 checkpoint used by ComfyUI**.
39
 
40
+
41
+
42
+
43
+ [Download workflow](https://huggingface.co/drbaph/MiniMax-H3-Turbo-Lora-ComfyUI/resolve/main/fl_minimax_h3_turbo_lora_example_workflow.json?download=true)
44
+ ![Screenshot 2026-08-06 070701](https://cdn-uploads.huggingface.co/production/uploads/63473b59e5c0717e6737b872/zfVV_yKP-njnOrGinGy8K.png)
45
+
46
  ## Original Project
47
 
48
  The original LoRA weights, training work, four-step distillation method, dual video/audio sampling implementation, documentation and source files were created and released by **larryvrh**:
 
60
  |---|---|
61
  | `minimax_h3_turbo_4step_pruned_comfyui.safetensors` | Partial ComfyUI compatibility conversion of the original trained non-EMA weights for the pruned/curve-form MiniMax-H3 checkpoint. The original author describes these weights as crisper and better at holding fast motion. |
62
  | `minimax_h3_turbo_4step_ema_pruned_comfyui.safetensors` | Partial ComfyUI compatibility conversion of the time-averaged EMA weights for the pruned/curve-form MiniMax-H3 checkpoint. The original author describes this early EMA checkpoint as smoother but softer and not yet fully matured. |
63
+ | `fl_minimax_h3_turbo_lora_example_workflow.json` | first & last frame comfyui example workflow using turbo lora + optional optimisations |
64
+
65
+
66
 
67
  The EMA and non-EMA files remain separate and contain different tensor values.
68