Verified: 4 months ago
Other
The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.
IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.
This clothes model can help you transfer clothes to a model, but I think this is far from enough, because you cannot decide what the model looks like. Then we add a pullid node, upload the model portrait, and then we can specify the clothes and models.
#182
1.LLM Model:
•The large language model group will download automatically during the first run.
•If the download fails, you can manually download the files and place them in the following folder:
ComfyUI/models/LLM/unsloth--Meta-Llama-3.1-8B-Instruct
•Download link: https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct (download all files).
2.Clip Vision:
•Download all files from:
https://huggingface.co/google/siglip-so400m-patch14-384/tree/main.
•Place them in the folder:
ComfyUI/models/clip_vision/google--siglip-so400m-patch14-384.
3.Joy Caption LoRA:
•Download all files from: https://huggingface.co/spaces/fancyfeast/joy-caption-alpha-two.
•Place them in the folder:
ComfyUI/models/Joy_caption/cgrkzexw-599808.
4.Precision Settings:
•Use bf16 for 3090/4090 GPUs.
•Otherwise, use nf4.
#123
1.PuLID Model:
•Used for facial reference.
•After downloading, place it in the models/controlnet/flux folder.
•Download link: https://huggingface.co/guozinan/PuLID/tree/main.
•The latest version is flux v0.9.1.
2.EVA CLIP:
•This is EVA02-CLIP-L-14-336 and should download automatically (located in the Hugging Face directory).
•If for any reason the automatic download fails, manually download the EVA-CLIP model, place the files in ComfyUI/models/clip, and restart ComfyUI.
•Download link: https://huggingface.co/QuanSun/EVA-CLIP/tree/main.
•Choose the file: EVA02_CLIP_L_336_psz14_s6B.pt.
3.InsightFace Model:
•Requires InsightFace with AntelopeV2.
•Extract the model and place it in ComfyUI/models/insightface/models/antelopev2.
•Download link: https://huggingface.co/MonsterMMORPG/tools/tree/main.
Note:
•This model frequently encounters errors and typically only works on 4090 GPUs, as other GPUs will likely throw errors.
•Errors often occur due to ComfyUI updates. If you frequently use this plugin, avoid updating ComfyUI randomly to ensure stability.
#38
This uses the Flux Dev ControlNet Inpainting Beta model from Alimama Studio.
•After downloading, place the files in the models/controlnet/flux folder.
•Download link: https://huggingface.co/alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta/tree/main.
#98
1.Prompt:
Enter the object to be separated, such as clothes, skirt, etc., to describe the clothing item.
2.Sort Method:
•This is index-based sorting.
•Left to right means sorting from left to right.
•Select Index: Choose which box to select.
#99 Florence2 Model:
•The model will download automatically during the first run. The base version is recommended.
•Download the model group into the models/florence2 folder.
•Download links:
•https://huggingface.co/MiaoshouAI/Florence-2-large-PromptGen-v1.5/tree/main
•https://huggingface.co/MiaoshouAI/Florence-2-base-PromptGen-v1.5/tree/main
#92
1.Segment Anything v2:
•Download the model to the models/sam2 folder.
•Model download link: https://huggingface.co/camenduru/segment-anything-2/tree/main.
2.Detail Method:
•This refers to the edge processing method. VitMatte is recommended.
•During the first run, it will download automatically. From the second run onwards, you can select VitMatte (local).
•If the first run download fails, you can manually download and place it in the models/vitmatte folder.
•Download link: https://huggingface.co/shiertier/vitmatte/tree/main.
•If an error occurs during execution, you can choose PyMatting instead. The results are slightly inferior but will avoid errors.
#31
It is recommended to use the FP8 model.
#25 InContext-LoRA
Model download link: https://huggingface.co/TTPlanet/Migration_Lora_flux/tree/main
INPUT
1.Model Image:
If pulid is enabled, turn it on and input the model’s portrait image here. If pulid is disabled, turn it off.
2.Model Text:
Describe the model in simple terms, e.g., a blonde female.
3.Clothes Image:
Input the clothing image here.
4.Clothes Text:
There are two ways to input clothing prompts, either manually or using Joy Caption:
•4-1: Manual Input
•Set input to 1.
•Disable the generate clothes text node group.
•4-2: Joy Caption Reverse-Engineering
•Set input to 2.
•Disable the input clothes text node group.