This workflow is local-only: it runs in your own ComfyUI installation and has no RunningHub workflow page in the source material. Files are in the Hugging Face / ModelScope package for episode 280.
Krea 2 Advanced Cleanup - Local Folder Batch (Structure LoRA + Reverse Prompt)
Purpose: the local folder-loop variant of the Krea 2 cleanup set. Point it at a folder of images; each image is reverse-prompted and rebuilt independently through depth-structure conditioning and the 4x upscale, then saved one by one.
Graph (as saved)
57 nodes / 98 links / 10 groups.
- Model: UNETLoader
krea2_turbo_fp8.safetensors; CLIPLoaderqwen3vl_4b_fp8_scaled.safetensors(typekrea2); VAELoaderqwen_image_HDR_vae_fp32_comfy.safetensors. - Structure LoRA: one
Krea2ControlLoRALoaderondepth-control-lora.safetensorsat strength 1.0. - Three depth stages: three
Krea2ControlImageEncode→Krea2ControlApplypairs driven by DA3 depth maps. - Batch loop:
easy loadImagesForLoop+easy forLoopEnd+easy batchAnything; each image is processed independently (the saved note is explicit that results are not reused across a batch). - Sampling: three KSamplers at 8 steps / CFG 1 / euler / simple with denoise 0.95, 0.35 and 0.25; two
LatentUpscalenodes (bislerp, 1024) saved disabled; final 4x-UltraSharp upscale. - Reverse prompt: Qwen3VLProcessor (open route) and RH_LLMAPI_Pro_Node (closed route, GLM-4.6V label);
ConditioningKrea2Rebalanceis active in this variant. - Output: SaveImage prefix
Krea2_本地批量洗图/Krea2_batch. - Saved-state inconsistency: the in-graph Note text still says "线上批量版" (online batch), but the actual nodes are a local folder loop and the output path is the local-batch path. The node graph is what runs; the note text is stale.
How to use
Point the loop loader at your folder, set the render stages / final long edge / reverse-prompt source in the console, and queue. Because this workflow is local-only, expect local VRAM and time costs — the online variant exists as a separate graph.
Limits and not-verified items
No inference was run for this listing: no speed, VRAM, batch throughput or quality claim is made. The saved notes are the author's configuration, not measured results. Weights, LoRA, depth model, upscaler and VLM routes are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: YouTube · Bilibili. Workflows supplied through AI-KSK; verify workflow, node, model, LoRA, depth model and cover rights separately. No blanket commercial or redistribution license is asserted.
Description
This workflow is local-only: it runs in your own ComfyUI installation and has no RunningHub workflow page in the source material. Files are in the Hugging Face / ModelScope package for episode 280.
Krea 2 Advanced Cleanup - Local Folder Batch (Structure LoRA + Reverse Prompt)Purpose: the local folder-loop variant of the Krea 2 cleanup set. Point it at a folder of images; each image is reverse-prompted and rebuilt independently through depth-structure conditioning and the 4x upscale, then saved one by one.
Graph (as saved)57 nodes / 98 links / 10 groups.
- Model: UNETLoader
krea2_turbo_fp8.safetensors; CLIPLoaderqwen3vl_4b_fp8_scaled.safetensors(typekrea2); VAELoaderqwen_image_HDR_vae_fp32_comfy.safetensors. - Structure LoRA: one
Krea2ControlLoRALoaderondepth-control-lora.safetensorsat strength 1.0. - Three depth stages: three
Krea2ControlImageEncode→Krea2ControlApplypairs driven by DA3 depth maps. - Batch loop:
easy loadImagesForLoop+easy forLoopEnd+easy batchAnything; each image is processed independently (the saved note is explicit that results are not reused across a batch). - Sampling: three KSamplers at 8 steps / CFG 1 / euler / simple with denoise 0.95, 0.35 and 0.25; two
LatentUpscalenodes (bislerp, 1024) saved disabled; final 4x-UltraSharp upscale. - Reverse prompt: Qwen3VLProcessor (open route) and RH_LLMAPI_Pro_Node (closed route, GLM-4.6V label);
ConditioningKrea2Rebalanceis active in this variant. - Output: SaveImage prefix
Krea2_本地批量洗图/Krea2_batch. - Saved-state inconsistency: the in-graph Note text still says "线上批量版" (online batch), but the actual nodes are a local folder loop and the output path is the local-batch path. The node graph is what runs; the note text is stale.
Point the loop loader at your folder, set the render stages / final long edge / reverse-prompt source in the console, and queue. Because this workflow is local-only, expect local VRAM and time costs — the online variant exists as a separate graph.
Limits and not-verified itemsNo inference was run for this listing: no speed, VRAM, batch throughput or quality claim is made. The saved notes are the author's configuration, not measured results. Weights, LoRA, depth model, upscaler and VLM routes are not bundled; check their licenses separately. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: YouTube · Bilibili. Workflows supplied through AI-KSK; verify workflow, node, model, LoRA, depth model and cover rights separately. No blanket commercial or redistribution license is asserted.