ComfyUI Extension: comfyui-replicate
Run Replicate models as nodes in ComfyUI
Custom Nodes (62)
- Replicate ai-forever/kandinsky-2
- Replicate ai-forever/kandinsky-2.2
- Replicate andreasjansson/blip-2
- Replicate andreasjansson/deepfloyd-if
- Replicate batouresearch/high-resolution-controlnet-tile
- Replicate batouresearch/magic-image-refiner
- Replicate batouresearch/magic-style-transfer
- Replicate black-forest-labs/flux-1.1-pro
- Replicate black-forest-labs/flux-dev
- Replicate black-forest-labs/flux-pro
- Replicate black-forest-labs/flux-schnell
- Replicate bytedance/sdxl-lightning-4step
- Replicate cjwbw/hyper-sdxl-1step-t2i
- Replicate cjwbw/pixart-sigma
- Replicate cjwbw/seamless_communication
- Replicate cjwbw/supir
- Replicate cuuupid/glm-4v-9b
- Replicate cuuupid/idm-vton
- Replicate declare-lab/tango
- Replicate fofr/consistent-character
- Replicate fofr/controlnet-preprocessors
- Replicate fofr/face-to-many
- Replicate fofr/latent-consistency-model
- Replicate fofr/sd3-with-chaos
- Replicate fofr/style-transfer
- Replicate fofr/ultrapixel
- Replicate ideogram-ai/ideogram-v2
- Replicate ideogram-ai/ideogram-v2-turbo
- Replicate lucataco/hunyuandit-v1.1
- Replicate lucataco/llama-3-vision-alpha
- Replicate lucataco/magnet
- Replicate lucataco/moondream2
- Replicate lucataco/paligemma-3b-pt-224
- Replicate lucataco/pasd-magnify
- Replicate lucataco/qwen-vl-chat
- Replicate lucataco/sdxl-clip-interrogator
- Replicate lucataco/xtts-v2
- Replicate luosiallen/latent-consistency-model
- Replicate meta/llama-2-70b-chat
- Replicate meta/llama-2-7b-chat
- Replicate meta/meta-llama-3.1-405b-instruct
- Replicate meta/meta-llama-3-70b-instruct
- Replicate meta/meta-llama-3-8b-instruct
- Replicate meta/musicgen
- Replicate nateraw/audio-super-resolution
- Replicate nateraw/musicgen-songstarter-v0.2
- Replicate omniedgeio/face-swap
- Replicate pharmapsychotic/clip-interrogator
- Replicate philz1337x/clarity-upscaler
- Replicate recraft-ai/recraft-v3
- Replicate salesforce/blip
- Replicate smoretalk/rembg-enhance
- Replicate snowflake/snowflake-arctic-instruct
- Replicate stability-ai/sdxl
- Replicate stability-ai/stable-diffusion
- Replicate stability-ai/stable-diffusion-3
- Replicate suno-ai/bark
- Replicate tstramer/material-diffusion
- Replicate yorickvp/llava-13b
- Replicate yorickvp/llava-v1.6-34b
- Replicate yorickvp/llava-v1.6-mistral-7b
- Replicate zsxkib/realistic-voice-cloning
README
comfyui-replicate
Custom nodes for running Replicate models in ComfyUI.
Take a look at the example workflows and the supported Replicate models to get started.
Set your Replicate API token before running
Make sure you set your REPLICATE_API_TOKEN in your environment. Get your API tokens here, we recommend creating a new one:
https://replicate.com/account/api-tokens
To pass in your API token when running ComfyUI you could do:
On MacOS or Linux:
export REPLICATE_API_TOKEN="r8_************"; python main.py
On Windows:
set REPLICATE_API_TOKEN="r8_************"; python main.py
Direct installation
cd ComfyUI/custom-nodes
git clone https://github.com/replicate/comfyui-replicate
cd comfyui-replicate
pip install -r requirements.txt
Supported Replicate models
View the supported_models.json
to see which models are packaged by default.
Update Replicate models
Simply run ./import_schemas.py
to update all model nodes. The latest version of a model is used by default.
Add more models
Only models that return simple text or image outputs are currently supported. If a model returns audio, video, JSON objects or a combination of outputs, the node will not work as expected.
If you want to add more models, you can:
- add the model to
supported_models.json
(for example,fofr/consistent-character
) - run
./import_schemas.py
, this will update all schemas and import your new model - restart ComfyUI
- use the model in workflow, it’ll have the title ‘Replicate [model author/model name]’
Roadmap
Things to investigate and add to this custom node package:
- support for more types of Replicate model (audio and video first)
- showing logs, prediction status and progress (via tqdm)
Contributing
If you add models that others would find useful, feel free to raise PRs.