root/local-ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Document multi-LoRA chaining and clarify no keyword triggers

Browse Source 
- README: Add "Combining multiple LoRAs" section with wiring diagram,
  expand style management table with combo examples, clarify that
  LoRAs are baked into workflows with no chat keyword activation
- Script: Add multi-LoRA tip and clarify no-keyword behavior

https://claude.ai/code/session_01PtYTPherSJaxDEVPgF6Nxu
This commit is contained in:
Claude
2026-03-22 20:16:54 +00:00
parent 84afe5c571
commit 40a0b6c1bf
2 changed files with 28 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+21 -5
View File
@@ -341,15 +341,31 @@ docker cp ~/Downloads/my-style-lora.safetensors comfyui:/opt/ComfyUI/models/lora
Now every "Generate an image of..." in chat uses your LoRA automatically. Now every "Generate an image of..." in chat uses your LoRA automatically.
#### Combining multiple LoRAs in one image
You can chain multiple Load LoRA nodes to blend styles:
```
[Load Checkpoint] → [Load LoRA 1] → [Load LoRA 2] → [KSampler]
(anime, 0.7) (lighting, 0.5)
```
Each LoRA has its own `strength_model` / `strength_clip` sliders. Export the combined workflow as usual — both LoRAs are baked in and always applied.
#### Managing multiple LoRA styles #### Managing multiple LoRA styles
Each LoRA needs its own exported workflow. Practical approach: Each LoRA combo needs its own exported workflow. Practical approach:
1. Build a workflow per style (e.g. `anime-lora.json`, `photorealistic-lora.json`) | Workflow file | LoRAs | Use case |
2. Switch between them in **Admin → Settings → Images → Import Workflow** |---------------|-------|----------|
3. The active workflow applies to all image generation requests | `anime-only.json` | Anime @ 0.8 | Anime style |
| `anime-cinematic.json` | Anime @ 0.7 + Cinematic @ 0.5 | Anime + dramatic lighting |
| `photorealistic.json` | Photorealistic @ 0.9 | Photo look |
| `base-model.json` | None | No LoRA, base checkpoint only |
> **Limitation:** You can't switch LoRAs dynamically from chat or adjust LoRA weight per-message. The workflow JSON is fixed. To change styles, swap the workflow in OWUI settings. Switch between them in **Admin → Settings → Images → Import Workflow**. The active workflow applies to all image generation requests.
> **Important:** There are no keywords or trigger words to activate LoRAs from chat. LoRAs are hardwired in the workflow JSON — whatever prompt you type, the LoRA(s) always apply. To change styles, swap the workflow in OWUI settings.
#### LoRA compatibility #### LoRA compatibility
comfyui-import-lora.sh
+7 -1
View File
@@ -87,5 +87,11 @@ echo ""
echo -e "${YELLOW}Tip:${NC} The LoRA must match your base model architecture." echo -e "${YELLOW}Tip:${NC} The LoRA must match your base model architecture."
echo " SD 1.5 LoRA → SD 1.5 checkpoint. SDXL LoRA → SDXL checkpoint." echo " SD 1.5 LoRA → SD 1.5 checkpoint. SDXL LoRA → SDXL checkpoint."
echo "" echo ""
echo -e "${YELLOW}Tip:${NC} Export multiple workflows (one per LoRA/style) and switch" echo -e "${YELLOW}Tip:${NC} You can ${BOLD}chain multiple LoRAs${NC} in one workflow:"
echo " [Checkpoint] → [Load LoRA 1] → [Load LoRA 2] → [KSampler]"
echo " Each has its own strength slider so you can blend styles."
echo ""
echo -e "${YELLOW}Tip:${NC} Export multiple workflows (one per LoRA combo) and switch"
echo " between them in Open WebUI's image settings as needed." echo " between them in Open WebUI's image settings as needed."
echo " LoRAs are baked into the workflow — there's no keyword to"
echo " toggle them on/off from chat."