Depth map reference, scene element replacement, style replacement, Flux.2 Klein. Online trial: Register to receive 1000 RH tokens, enough to process dozens or even hundreds of images. Daily login earns 100 tokens,...
Laufzeitprofil
Quellenbeschreibung
Depth map reference, scene element replacement, style replacement, Flux.2 Klein. Online trial: https://www.runninghub.ai/post/2016685462710132737/?inviteCode=rh-v1479 Register to receive 1000 RH tokens, enough to process dozens or even hundreds of images. Daily login earns 100 tokens, practically free.
Video tutorial: https://www.bilibili.com/video/BV1eF6FB9EY2/?spm_id_from=333.1387.homepage.video_card.click&vd_source=40273246c265c4ea46769c49fe4beb66
KI-generierter Kommentar
KI-generierte Erklärung auf Grundlage von Quellen- und Konfigurationsdetails. Vorschläge sind klar gekennzeichnet.
This workflow is for image editing with a depth-map reference. It can replace scene elements or style with Flux.2 Klein 9B, using an image and prompt text and producing preview and saved-image outputs.
The 19-node graph moves from image loading and preprocessing through prompt handling, image editing, sampling, decoding, preview, and saving.
LoadImage, AIO_Preprocessor, CR Prompt Text, and CR Text Concatenate handle the image and prompt text.
PreviewImage and SaveImage provide the preview and saved-image stages.
The workflow is listed on Civitai and attributed to DUDU0627.
The listing includes an online trial and a video tutorial.
The workflow names these node packs: cg-use-everywhere, ComfyUI_Comfyroll_CustomNodes, comfyui-custom-scripts, comfyui-easy-use, comfyui_controlnet_aux, and llama-cpp_vllm.
The named model files are flux-2-klein-9b.safetensors, flux2-vae.safetensors, qwen_3_8b_fp8mixed.safetensors, Qwen3-VL-8B-Instruct-abliterated-v2.0.mmproj-Q8_0.gguf, and Qwen3-VL-8B-Instruct-abliterated-v2.0.Q8_0.gguf.
The listed base model is Flux.2 Klein 9B.
Before use, verify that these six node packs and five model files are available under the names listed above.
Vorschlag · nicht geprüft
No license is listed for this workflow.
Muss das bearbeitet werden?
Melden Sie sich an, um eine Änderungsanfrage zu senden.
Quellen
1 QuelleQuellenauszüge
1 AuszugSource context: 307 downloads · Type Workflows · Base model Flux.2 Klein 9B
Geschätzter VRAM Bedarf
Schätzung nicht verfügbar
25,0 GB über 2 von 5 Modell-Dateien. Gesamtmodell-Dateien + 25% Ladeaufwand + 2 GB Ausführungs-Puffer, aufgerundet.
Anforderungen
11 AnforderungenCheckpoint · 16.9 GB · SAFETENSORS · bf16 · full · Unknown
flux2-vae.safetensors
MöglichVAE · Unknown
qwen_3_8b_fp8mixed.safetensors
GefundenText encoder · 8.07 GB · SAFETENSORS · fp16 · Unknown
Qwen3-VL-8B-Instruct-abliterated-v2.0.mmproj-Q8_0.gguf
Nicht aufgelöstText encoder · Unknown
Qwen3-VL-8B-Instruct-abliterated-v2.0.Q8_0.gguf
Nicht aufgelöstText encoder · Unknown
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
Knotenpaket · Registry
llama-cpp_vllm
Nicht aufgelöstKnotenpaket · Registry