cychenyue

说明文档<a href="https://xiaobot.net/post/a4f089b5-d74b-4182-947a-3932eb73b822" target="_blank">https://xiaobot.net/post/a4f089b5-d74b-4182-947a-3932eb73b822</a>由于AI技术更新迭代，请以文档更新为准更多内容收录在⬇️<a href="https://xiaobot.net/p/GoToComfyUI" target="_blank">https://xiaobot.net/p/GoToComfyUI</a>网盘<a href="https://pan.quark.cn/s/00b3b6fcd6ca" target="_blank">https://pan.quark.cn/s/00b3b6fcd6ca</a>ComfyUI-MiniCPM-Plus节点<a href="https://github.com/CY-CHENYUE/ComfyUI-MiniCPM-Plus" target="_blank">https://github.com/CY-CHENYUE/ComfyUI-MiniCPM-Plus</a>video<a href="https://youtu.be/JJ8u8WnYidY" target="_blank">https://youtu.be/JJ8u8WnYidY</a>

 Image To Prompt and  Text To Prompt

duitpower_87490

Use this workflow to test your trained lora.

Flux Lora to test Trained Lora

ᴅᴇᴀᴅɪᴄᴇ

Swap faces in under 20 seconds with this efficient workflow, utilizing the SDXL Turbo model to generate the base image, followed by face swapping through Reactor for seamless integration of the input face.

Fast Face Swap 

Shubz World

Best Performance Setup for FLUX with LoRA on ComfyUI A TUTORIAL WILL BE COMING FOR BEST WORKFLOWS SUBSCRIBE CHANNEL FOR UPDATES: <a href="https://www.youtube.com/@CSCPRINTSHOPPORTAL" target="_blank">https://www.youtube.com/@CSCPRINTSHOPPORTAL</a> Step 1: Define Your Batch Image LocationChoose your default location for batch image outputs when using ComfyUI. Example folder path:D:\AI_GENRATION\ComfyUI_WORKING\ComfyUI\custom_nodes\ComfyUI-Inspire-Pack\prompts\cartoon\fluxbatch1.txt --- #### Step 2: Text File Format for PromptsFollow this exact format when creating your text file. The positive and negative prompts should be formatted as shown, with the correct number of minuses in between. **Text Format Example:** positive: A mysterious sorcerer, cloaked in dark robes, stands in a candlelit chamber filled with ancient scrolls and magical artifacts. His hands glow with swirling energy as he prepares a powerful spell, his face shrouded in shadow. The atmosphere is mystical and ominous. &lt;lora:Cute_3d_Cartoon_Flux:0.7&gt; &nbsp;negative: &nbsp;---------------- positive: A steampunk-inspired airship flying over a bustling Victorian city. The ship is adorned with brass gears and smokestacks, and the sky is filled with clouds and other flying vessels. The scene is full of adventure and mechanical wonder. &lt;lora:Cute_3d_Cartoon_Flux:0.7&gt; &nbsp;negative: &nbsp;----positive: A cute, chubby dragon sits atop a pile of colorful, glowing gemstones in a cozy cave. Its scales shimmer in the light, and its wide eyes are filled with curiosity and mischief. The style is playful and whimsical, capturing the dragon’s endearing charm. &lt;lora:Cute_3d_Cartoon_Flux:0.7&gt; &nbsp;negative: ---- #### Step 3: My System Specifications for &nbsp;These Results- **GPU:** RTX 4050 6GB VRAM- **RAM:** 16GB- **Processor:** Intel i5-13420H **Performance:** &nbsp;For **20 steps** with **Guidance Scale 4**: &nbsp;- **With LoRA:** Generation time: 02:25 (7.27 seconds/iteration) &nbsp;- **Without LoRA:** Generation time: 02:07 (6.35 seconds/iteration) &nbsp; **Resolution:** Use a landscape ratio of 1360x768. &nbsp;OPTIONAL --- #### Step 4: GGUF Version for Low VRAM UsersIf using the GGUF version of FLUX, this setup works well on lower VRAM systems. - **My System Specs Using GGUF:** &nbsp; &nbsp;- **GPU:** RTX 4050 6GB VRAM &nbsp; &nbsp;- **RAM:** 16GB &nbsp; &nbsp;- **Processor:** Intel i5-13420H For **20 steps** with LoRA enabled: &nbsp;- **Generation Time:** 02:25 (7.27 seconds/iteration) --- #### Step 5: Downloads 1. **FLUX Model (FP8):** &nbsp; &nbsp; Download the FLUX UNET model from the following link: &nbsp; &nbsp; https://huggingface.co/Kijai/flux-fp8/tree/main 2. **LoRA Model for Cute 3D Cartoon:** &nbsp; &nbsp; Download the LoRA model here: &nbsp; &nbsp; https://civitai.com/models/677725/cute-3d-cartoon-flux 3. **GGUF Version Downloads:** &nbsp; &nbsp; - **UNET GGUF Model:** https://huggingface.co/city96/FLUX.1-dev-gguf/tree/main &nbsp; &nbsp; - **CLIP T5 GGUF:** https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/tree/main &nbsp; &nbsp; - **CLIP L (safetensors):** https://huggingface.co/comfyanonymous/flux_text_encoders/blob/main/clip_l.safetensors --- #### Step 6: Model LocationsEnsure you place the downloaded models in the correct directories: - **UNET Model Location:** &nbsp; D:\AI_GENRATION\ComfyUI_WORKING\ComfyUI\models\unet - **LoRA Model Location:** &nbsp; &nbsp;D:\AI_GENRATION\ComfyUI_WORKING\ComfyUI\models\lora - **GGUF Model Location:** &nbsp; &nbsp;D:\AI_GENRATION\ComfyUI_WORKING\ComfyUI\models\unet - **CLIP L Location:** &nbsp; D:\AI_GENRATION\ComfyUI_WORKING\ComfyUI\models\clip - **CLIP T5 Location:** &nbsp; &nbsp;D:\AI_GENRATION\ComfyUI_WORKING\ComfyUI\models\clip\t5 Hey, awesome human! If you’ve got an extra coffee lying around (or, you know, the cost of one), I’d love to turn it into creative fuel! ☕️ It’s like magic beans, but instead of a beanstalk, you get more cool content. Thanks for keeping me caffeinated and inspired!<a href="https://buymeacoffee.com/shubzworld" target="_blank">https://buymeacoffee.com/shubzworld</a>

OpenArt

Workflows

All Workflows

Active Sessions

All ComfyUI Workflows

Loading...