Comfyanonymous examples. The text box GLIGEN model lets you specify the location and size of multiple objects in the image. Hunyuan DiT Examples. safetensors and put it in your ComfyUI/checkpoints directory. safetensors from this page and save it as t5_base. Hypernetworks are patches applied on the main MODEL so to use them put them in the models/hypernetworks directory and use the Hypernetwork Loader node like this: You can apply multiple hypernetworks by chaining multiple Hypernetwork Loader nodes in sequence. For the easy to use single file versions that you can easily use in ComfyUI see below: FP8 Checkpoint Version. User profile of comfy on Hugging Face. It basically lets you use images in your prompt. Installing. - Releases · comfyanonymous/ComfyUI You signed in with another tab or window. Lora Examples. Here is the input image I used for this workflow: T2I-Adapter vs ControlNets. io/Comf In this example we will be using this image. 31 seconds, it throws an exception Steps to Reproduce Upload the example workflow for DEV version https://comfyanonymous. Hires fix is just creating an image at a lower resolution, upscaling it and then sending it through img2img. T2I-Adapters are much much more efficient than ControlNets so I highly recommend them. Stable Zero123 is a diffusion model that given an image with an object and a simple background can generate images of that object from different angles. This is what the workflow looks like in ComfyUI: SDXL Examples. To use it properly you should write your prompt normally then use the GLIGEN Textbox Apply nodes to specify where you want certain objects/concepts in your prompts to be in the image. Nodes/graph/flowchart interface to experiment and create complex Stable Diffusion workflows without needing to code anything. Since general shapes like poses and subjects are denoised in the first sampling steps this lets us for example position subjects with specific poses anywhere on the image while keeping a great amount of consistency. Capture UI events. XLab and InstantX + Shakker Labs have released Controlnets for Flux. Area composition with Anything-V3 + second pass with AbyssOrangeMix2_hard. AuraFlow Examples. com/comfyanonymous/ComfyUI. You can find the InstantX Canny model file here (rename to instantx_flux_canny. Contribute to comfyanonymous/ComfyUI_examples development by creating an account on GitHub. Flux is a family of diffusion models by black forest labs. Stable cascade is a 3 stage process, first a low resolution latent image is generated with the Stage C diffusion model. You can then load up the following image in ComfyUI to get the workflow: AuraFlow 0. unCLIP models are versions of SD models that are specially tuned to receive image concepts as input in addition to your text prompt. comfyanonymous/Freeway_Animation_Hunyuan_Demo_ComfyUI_Converted ComfyUI. Regular Full Version Files to download for the regular version Video Examples Image to Video. This first example is a basic example of a simple merge between two different checkpoints. Here are the official checkpoints for the one tuned to generate 14 frame videos and the one for 25 frame videos. These examples are done with the WD1. The LCM SDXL lora can be downloaded from here. x, SDXL, Stable Video Diffusion, Stable Cascade, SD3 and Stable Audio. Download it, rename it to: lcm_lora_sdxl. In this example we will be using this image. 1 Schnell; Overview: Cutting-edge performance in image generation with top-notch prompt following, visual quality, image detail, and output diversity. Text box GLIGEN. As of writing this there are two image to video checkpoints. LCM loras are loras that can be used to convert a regular model to a LCM model. 1 Hypernetwork Examples. Put them in the models/upscale_models folder then use the UpscaleModelLoader node to load them and the ImageUpscaleWithModel node to use them. Apr 5, 2023 · You signed in with another tab or window. Upscale Model Examples. 5GB) and sd3_medium_incl_clips_t5xxlfp8. SDXL Turbo is a SDXL model that can generate consistent images in a single step. Flux. 8 for example is the same as setting both strength_model and strength_clip to 0. ComfyUI Examples. 5 beta 3 illusion model. This repo contains examples of what is achievable with ComfyUI. 3D Examples Stable Zero123. You switched accounts on another tab or window. Instead, you can use Impact/Inspire Pack's KSampler with Negative Cond Placeholder. In ComfyUI the saved checkpoints contain the full workflow used to generate them so they can be loaded in the UI just like images to get the full workflow that was used to create them. Image Edit Model Examples. 1 Pro Flux. Follow their code on GitHub. Here is an example for how to use Textual Inversion/Embeddings. Note that in ComfyUI txt2img and img2img are the same node. Aug 1, 2024 · Expected Behavior Run the inference Actual Behavior After 273. Regular KSampler is incompatible with FLUX. safetensors to your ComfyUI/models/clip/ directory. Ctrl + C/Ctrl + V Copy and paste selected nodes (without maintaining connections to outputs of unselected nodes) Ctrl + C/Ctrl + Shift + V Copy and paste selected nodes (maintaining connections from outputs of unselected nodes to inputs of pasted nodes) There is a portable standalone build for 2 Pass Txt2Img (Hires fix) Examples. Download it and place it in your input folder. Blog Learn how to create stunning UI designs with ComfyUI, a powerful tool that integrates with ThinkDiffusion. Dec 5, 2023 · This ui will let you design and execute advanced stable diffusion pipelines using a graph/nodes/flowchart based interface. setup() is a good place to do this, since the page has fully loaded. You can use more steps to increase the quality. The SDXL base checkpoint can be used like any regular checkpoint in ComfyUI. This latent is then upscaled using the Stage B diffusion model. To give you an idea of how powerful it is: StabilityAI, the creators of Stable Diffusion, use ComfyUI to test Stable Diffusion internally. pt embedding in the previous picture. Examples page. com Flux Examples. These are examples demonstrating how you can achieve the “Hires Fix” feature. [1] ComfyUI looks Feature/Version Flux. Hunyuan DiT is a diffusion model that understands both english and chinese. Edit models also called InstructPix2Pix models are models that can be used to edit images using a text prompt. If using GIMP make sure you save the values of the transparent pixels for best results. safetensors for the example below), the Depth controlnet here and the Union Controlnet here. Here is a link to download pruned versions of the supported GLIGEN model files. GLIGEN Examples. Action Movies & Series; Animated Movies & Series; Comedy Movies & Series; Crime, Mystery, & Thriller Movies & Series; Documentary Movies & Series; Drama Movies & Series In most UIs adjusting the LoRA strength is only one number and setting the lora strength to 0. Features. All the images in this repo contain metadata which means they can be loaded into ComfyUI with the Load button (or dragged onto the window) to get the full workflow that was used to create the image. LCM Examples. Images are encoded using the CLIPVision these models come with and then the concepts extracted by it are passed to the main model when sampling. x, SD2. 1GB) can be used like any regular checkpoint in ComfyUI. ComfyUI Examples. Here is an example of how to use upscale models like ESRGAN. Hunyuan DiT 1. Here is the workflow for the stability SDXL edit model, the checkpoint can be downloaded from: here. 1 background image and 3 subjects. - comfyanonymous/ComfyUI SDXL Turbo Examples. - comfyanonymous/ComfyUI. Put them in the ComfyUI/models/checkpoints folder. The proper way unCLIP Model Examples. This upscaled latent is then upscaled again and converted to pixel space by the Stage A VAE. . Installing ComfyUI. Download hunyuan_dit_1. Put the GLIGEN model files in the ComfyUI/models/gligen directory. AuraFlow 0. All LoRA flavours: Lycoris, loha, lokr, locon, etc… are used this way. This image has had part of it erased to alpha with gimp, the alpha channel is what we will be using as a mask for the inpainting. 0. For some workflow examples and see what ComfyUI can do you can check out: ComfyUI Examples Installing ComfyUI Features The text box GLIGEN model lets you specify the location and size of multiple objects in the image. Audio Examples Stable Audio Open 1. You signed out in another tab or window. To use an embedding put the file in the models/embeddings folder then use it in your prompt like I used the SDA768. These are examples demonstrating how to do img2img. Examples of ComfyUI workflows. AuraFlow is one of the only true open source models with both the code and the weights being under a FOSS license. Note that in these examples the raw image is passed directly to the ControlNet/T2I adapter. 2. - GitHub - comfyanonymous/ComfyUI at therundown website ComfyUI. Mar 22, 2023 · I tried looking at the examples to see if I could spot a pattern in use cases; I noticed the "simple" sample type was used in the Img2Img type of examples, and Normal was used if it was the initial gen, but I'm not sure if this is the correct way for me to be interpreting these things. For example: 896x1152 or 1536x640 are good resolutions. safetensors (5. Img2Img works by loading an image like this example image, converting it to latent space with the VAE and then sampling on it with a denoise lower than 1. 1 Dev Flux. Download the model. You can Load these images in ComfyUI to get the full workflow. github. Reload to refresh your session. unCLIP Model Examples unCLIP models are versions of SD models that are specially tuned to receive image concepts as input in addition to your text prompt. If you want to use text prompts you can use this example: Note that the strength option can be used to increase the effect each input image has on the final output. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The difference between both these checkpoints is that the first contains only 2 text encoders: CLIP-L and CLIP-G while the other one Inpaint Examples. - comfyanonymous/ComfyUI The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. Each ControlNet/T2I adapter needs the image that is passed to it to be in a specific format like depthmaps, canny maps and so on depending on the specific model if you want good results. Fully supports SD1. Img2Img Examples. safetensors and put it in your ComfyUI/models/loras directory. In this following example the positive text prompt is zeroed out in order for the final output to follow the input image more closely. They have since hired Comfyanonymous to help them work on internal tools. The reason you can tune both in ComfyUI is because the CLIP and MODEL/UNET part of the LoRA will most likely have learned different concepts so tweaking them separately The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. pt You signed in with another tab or window. Aug 2, 2024 · You signed in with another tab or window. Here is an example: You can load this image in ComfyUI to get the workflow. The only important thing is that for optimal performance the resolution should be set to 1024x1024 or other resolutions with the same amount of pixels but a different aspect ratio. LCM models are special models that are meant to be sampled in very few steps. This example contains 4 images composited together. Explore 10 cool workflows and examples. LCM Lora. safetensors (10. You can load this image in ComfyUI to get the full workflow. Written by comfyanonymous and other contributors. Here is an example. Aug 2, 2024 · Good, i used CFG but it made the image blurry, i used regular KSampler node. Download aura_flow_0. These are examples demonstrating how to use Loras. 8. Asynchronous Queue system. See full list on github. The SD3 checkpoints that contain text encoders: sd3_medium_incl_clips. SD3 Examples. These are examples demonstrating the ConditioningSetArea node. Area Composition Examples. The total steps is 16. The most powerful and modular stable diffusion GUI and backend. - comfyanonymous/ComfyUI Textual Inversion Embeddings Examples. This image contain 4 different areas: night, evening, day, morning. comfyanonymous has 12 repositories available. Upscale Model Examples Here is an example of how to use upscale models like ESRGAN. With the positions of the subjects changed: You can see that the subjects that were composited from different noisy latent images actually interact with each other because I put "holding hands" in the prompt. Dec 19, 2023 · ComfyUI was created in January 2023 by Comfyanonymous, who created the tool to learn how Stable Diffusion works. Here’s a simple example of how to use controlnets, this example uses the scribble controlnet and the AnythingV3 model. Note that you can omit the filename extension so these two are equivalent: embedding:SDA768. You signed in with another tab or window. This works just like you’d expect - find the UI element in the DOM and add an eventListener. Github Repo: https://github. kcgdyyzkqvmpatoqydwvplayfzpcyfcistyioszoeczfvbnhhezxrxglp