20261101@1910EST: 9.4.1 is released as a hotfix for 9.4 issue with muting Stage0.
Simpler version of my now retired "Combined Workflow" split into three workflows.
## "combined"
This is the primary image generator that has supports for multiple image models for sampling (with about 500 custom nodes)
The workflow include an optional model resampler, VOSR2 upscalers, and Face and Eyes detailers.
See the embedded READ ME FIRST for usage details.
## "ModelTools"
Designed to be used with the original generation model, this workflow provide acces to 2x Model resamplers, an Inpainting detailers, SAM detailers with small/large distinction and a final VOSR2 upscaler (about 250 custom nodes).
See the embedded READ ME FIRST for usage details.
## "AltModelResampler"
Designed to be used with any image, this workflow will allow resampling of the intput image usign Flux1.D or Krea2 with some LoRAs and can create very different results from the source image (about 200 custom nodes).
See the embedded READ ME FIRST for usage details.
Description
- Added optional model randomization: replaced checkpoint/UNet loaders with LoRA Manager loaders (requires version 1.2.2 of LoraManager)
- Added optional LoRA randomization
- Expanded prompt enhancement: choose between local QwenVL, external/API models through ComfyUI LLM Party, or Ollama.
- Reworked the positive-prompt pipeline: separate LoRA Manager Pre-Prompt, Main Prompt, and Post-Prompt fields. Only the main prompt and optional image-derived description go through the LLM; trigger words, pre/post qualifiers, embeddings, and LoRA names are assembled afterward.
- Consolidated wildcard prompting into LoRA Manager.
- Rewritten LLM instructions for Narrative, Tags, and Narrative + Tags modes, emphasizing preservation of subject counts, actions, composition, and explicit details while reducing invented content.
- Added explicit "THEME=..." handling and refined weighted-tag handling.
- Revised image-to-prompt instructions to focus on visible details and avoid unsupported assumptions.
- Simplified img2img loading/resizing.
- Cleaned up generation subgraphs and wiring: removed unused outputs, switches, and inherited parameters.
- Expanded workflow notes, including a model-settings reference table, randomization guidance, prompt assembly explanation, and LLM setup instructions.