Tem um workflow do ComfyUI? Gere uma documentação legível direto no navegador.Torne um workflow legível.Experimentar agora ↗
The main goal of this ComfyUI workflow is to create two images: one with an anime look, and one with a realistic look. The two images should look relatively similar, and a video interpolating from one to the other...
Perfil de execução
Descrição da fonte
The main goal of this ComfyUI workflow is to create two images: one with an anime look, and one with a realistic look. The two images should look relatively similar, and a video interpolating from one to the other will be produced at the end.
The workflow itself features multiple latent techniques such as:
Noise injection
Latent upscale
Face detailer
...but all of these are optional, and the core feature is that, for the base generation (the very first group of KSamplers), the denoising process will branch from the anime model to the realistic model after a given amount of steps.
Comentário gerado por IA
Explicação gerada por IA com base nos detalhes da fonte e da configuração. As sugestões são claramente identificadas.
Anime To Realistic FLUX Workflow (NO CONTROLNET) is a ComfyUI workflow for generating two relatively similar images—one anime-looking and one realistic-looking—and a video that interpolates between them, with separate LoRa stacks, guidance scales, and prompt prefixes or suffixesᐧ
During base generation, denoising branches from the anime model to the realistic model after a chosen number of steps.
Each image then continues through later upscaling and face-detailing paths.
Set an independent LoRa stack, guidance scale, and prompt prefix or suffix for each image.
The outputs are an anime-looking image, a realistic-looking image, and a video interpolating between the two.
The .zip includes the JSON workflow and raw PNGs, which you can drag into ComfyUI to recreate the shared examples.
The listed base model is Flux.1 D.
The workflow lists these node packs: comfyui_essentials, comfyui-custom-scripts, comfyui-detail-daemon, comfyui-impact-pack, comfyui-kjnodes, comfyui-list-utils, and pr-was-node-suite-comfyui-47064894.
It also lists these model files: clip_l.safetensors, flux_1Dev.safetensors, and t5xxl_fp16.safetensors.
Noise injection, latent upscale, and face detailer are optional techniques.
With little modification, prompts and base models could be entirely different.
Before use, verify that pr-was-node-suite-comfyui-47064894 and flux_1Dev.safetensors are available in ComfyUI.
Sugestão · não verificado
If you need the realistic image’s LoRAs preserved through upscaling, review that setting before use.
Sugestão · não verificado
Isso precisa ser editado?
Faça login para enviar uma solicitação de edição.
Fontes
1 fonteTrechos de fonte
1 trechoSource context: 1542 downloads · Type Workflows · Base model Flux.1 D
Then, both images branch off for the later upscaling processes and face detailer.
The workflow allows to specify independent values for each image:
LoRa stack
Guidance scale
Prompts (suffixes and prefixes for simplicity)
With little modification prompts and base models could be entirely different, if you truly need it.
The LoRa stack for the realistic image is removing LoRas during the upscaling process as I've experienced the infamous "FLUX lines" in many of them.
The .zip file contains the JSON workflow as well as all the raw pngs, so you can easily drag-n-drop them in ComfyUI to recreate the images shared as examples.
Estimativa de requisito VRAM
Estimativa indisponível
9,34 GB distribuídos em 2 de 3 arquivos de modelo. Total de arquivos do modelo + 25% de overhead de carregamento + 2 GB de buffer de execução, arredondado para cima.
Requisitos
Requisitos 10Text encoder · 235 MB · SAFETENSORS · Unknown
flux_1Dev.safetensors
Não resolvidoCheckpoint · Unknown
Text encoder · 9.12 GB · SAFETENSORS · Unknown
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
Pacote de nós · Registry
pr-was-node-suite-comfyui-47064894
Não resolvidoPacote de nós · Registry
