feat: default lora_name to the bundled turbo LoRA for clone-and-go installs

This commit is contained in:
Z User 2026-09-26 21:14:29 +00:00
parent 659778c38c
commit a1c7f6786e
3 changed files with 29 additions and 17 deletions

View File

@ -6,6 +6,7 @@
### ⚡ Improvements ### ⚡ Improvements
- **Moxie Multimedia Loader**: The `lora_name` combo now defaults to the bundled turbo LoRA (`MM3step.safetensors`) so a fresh clone of the pack works out of the box, with a `none` entry to disable LoRA. Previously the default was a `"<no files found>"` placeholder, which silently skipped LoRA application even when a LoRA was bundled.
- **Moxie Preview Override**: The `tiny_vae` combo now lists files from the node pack's own `models/vae_approx` folder first (shipping `MM-preview.safetensors` for MiniMax H3 previews as the default), falling back to ComfyUI's standard `models/vae_approx` directory. The folder is rescanned on every schema refresh, so newly dropped files appear without restarting ComfyUI. - **Moxie Preview Override**: The `tiny_vae` combo now lists files from the node pack's own `models/vae_approx` folder first (shipping `MM-preview.safetensors` for MiniMax H3 previews as the default), falling back to ComfyUI's standard `models/vae_approx` directory. The folder is rescanned on every schema refresh, so newly dropped files appear without restarting ComfyUI.
- **Moxie Multimedia Loader**: Locked the loader to the MiniMax H3 model set. The `clip_type` dropdown (which previously exposed every CLIP recipe in ComfyUI) was removed; the H3 Qwen3-VL text encoder is now always loaded with the `minimax` CLIP recipe. Any older ComfyUI build without `CLIPType.MINIMAX` raises a clear startup error instead of silently loading the wrong encoder. - **Moxie Multimedia Loader**: Locked the loader to the MiniMax H3 model set. The `clip_type` dropdown (which previously exposed every CLIP recipe in ComfyUI) was removed; the H3 Qwen3-VL text encoder is now always loaded with the `minimax` CLIP recipe. Any older ComfyUI build without `CLIPType.MINIMAX` raises a clear startup error instead of silently loading the wrong encoder.
- **Moxie Multimedia Loader / Moxie MultiTrack Project**: Removed the legacy `FAST_MODEL_LOADER` (`model_loader`) bundle. The loader now outputs exactly `model`, `clip`, `video_vae`, and `audio_vae` (with the attention backend and LoRA already applied to the model), and the Moxie MultiTrack Project takes those four outputs as required direct inputs instead of a bundled loader. `Moxie Preview Override` likewise dropped its `model_loader` pass-through slots and now patches the `model` input directly. The generic `easy multitrackProject` node keeps its `model_loader` input for non-Moxie workflows. - **Moxie Multimedia Loader / Moxie MultiTrack Project**: Removed the legacy `FAST_MODEL_LOADER` (`model_loader`) bundle. The loader now outputs exactly `model`, `clip`, `video_vae`, and `audio_vae` (with the attention backend and LoRA already applied to the model), and the Moxie MultiTrack Project takes those four outputs as required direct inputs instead of a bundled loader. `Moxie Preview Override` likewise dropped its `model_loader` pass-through slots and now patches the `model` input directly. The generic `easy multitrackProject` node keeps its `model_loader` input for non-Moxie workflows.

View File

@ -56,24 +56,26 @@ cd Your_ComfyUI_Path/custom_nodes
git clone https://github.com/yolain/ComfyUI-Easy-Media.git git clone https://github.com/yolain/ComfyUI-Easy-Media.git
``` ```
### Downloading the models ### Models
The Moxie Multimedia Loader reads its model files from the pack's own `models/` subfolders. All model files ship **inside the repo** — cloning it into `custom_nodes` is all that's needed:
Run the bundled downloader to fetch the MiniMax H3 model set and place it with the expected names:
| File | Location |
|---|---|
| MiniMax H3 diffusion model (`Moxie-Multimedia.safetensors`) | `models/diffusion/` |
| Qwen3-VL text encoder (`MM-VL.safetensors`) | `models/clip/` |
| Video VAE (`video_vae.safetensors`) | `models/vae/` |
| Audio VAE (`audio_vae.safetensors`) | `models/audio_vae/` |
| 3-step turbo LoRA (`MM3step.safetensors`) | `models/loras/` (applied by default, `none` to disable) |
| Preview tiny VAE (`MM-preview.safetensors`) | `models/vae_approx/` |
If you obtained the pack without the bundled files, the bundled downloader fetches and places them
(idempotent + resumable — re-run if interrupted):
```bash ```bash
bash custom_nodes/MMnode/download_models.sh bash custom_nodes/MMnode/download_models.sh
``` ```
It downloads (idempotent + resumable — re-run if interrupted):
| File | Saved as |
|---|---|
| MiniMax H3 diffusion model | `models/diffusion/Moxie-Multimedia.safetensors` |
| Qwen3-VL text encoder | `models/clip/MM-VL.safetensors` |
| Video VAE | `models/vae/video_vae.safetensors` |
| Audio VAE | `models/audio_vae/audio_vae.safetensors` |
Restart ComfyUI afterwards so the loader dropdowns pick the files up. Restart ComfyUI afterwards so the loader dropdowns pick the files up.
## ✏️ Example Workflows ## ✏️ Example Workflows

View File

@ -78,7 +78,10 @@ class MoxieMultimediaLoader(io.ComfyNode):
@classmethod @classmethod
def define_schema(cls) -> io.Schema: def define_schema(cls) -> io.Schema:
lora_placeholder = "<no files found in models/loras>" # The published pack ships its models inside the repo, so default to
# the bundled turbo LoRA out of the box; "none" opts out.
lora_files = _list_files("loras")
lora_default = "none" if lora_files[0].startswith("<no files found") else lora_files[0]
return io.Schema( return io.Schema(
node_id="MoxieMultimediaLoader", node_id="MoxieMultimediaLoader",
display_name="Moxie Multimedia Loader", display_name="Moxie Multimedia Loader",
@ -107,9 +110,10 @@ class MoxieMultimediaLoader(io.ComfyNode):
), ),
io.Combo.Input( io.Combo.Input(
"lora_name", "lora_name",
options=_list_files("loras"), options=["none"] + lora_files,
default=lora_placeholder, default=lora_default,
tooltip="LoRA file (inside models/loras).", tooltip="LoRA file from the pack's models/loras folder, applied to both the model and "
"the CLIP. Defaults to the bundled turbo LoRA; 'none' disables it.",
), ),
io.Float.Input("lora_strength_model", default=1.0, min=-100.0, max=100.0, step=0.01, io.Float.Input("lora_strength_model", default=1.0, min=-100.0, max=100.0, step=0.01,
tooltip="How strongly the LoRA modifies the diffusion model."), tooltip="How strongly the LoRA modifies the diffusion model."),
@ -184,7 +188,12 @@ class MoxieMultimediaLoader(io.ComfyNode):
@classmethod @classmethod
def _apply_lora(cls, model, clip, lora_name, strength_model, strength_clip): def _apply_lora(cls, model, clip, lora_name, strength_model, strength_clip):
if lora_name.startswith("<no files found") or (strength_model == 0 and strength_clip == 0): if (
lora_name is None
or lora_name == "none"
or lora_name.startswith("<no files found")
or (strength_model == 0 and strength_clip == 0)
):
return model, clip return model, clip
lora_path = _resolve("loras", lora_name) lora_path = _resolve("loras", lora_name)