--- license: other tags: - text to image - image to image - upscale - inpainting - controlnet - depth - canny - openpose - vae - unet - pulid - redux - comfyui - flux - fill - sdxl - gguf - face swap - adetailer language: en pipeline_tag: text-to-image --- --- # πŸ“¦ ComfyUI-Starter-Packs > A curated vault of essential models for ComfyUI users β€” organized, curated, and ready. > No bloat. No hunting through 15 Civitai and Hugging Face repos. --- ## 🧐 What’s Inside
πŸ”§ Flux1 β”œβ”€β”€ Flux1 β”‚ β”œβ”€β”€ Controlnets β”‚ β”‚ β”œβ”€β”€ flux_shakker_labs_union_pro-fp8.safetensors β”‚ β”œβ”€β”€ LoRas β”‚ β”‚ β”œβ”€β”€ navi_flux_v1.safetensors β”‚ β”œβ”€β”€ PuLID β”‚ β”‚ β”œβ”€β”€ pulid_flux_v0.9.1.safetensors β”‚ β”œβ”€β”€ Style_Models β”‚ β”‚ β”œβ”€β”€ flux1-redux-dev.safetensors β”‚ β”œβ”€β”€ clip β”‚ β”‚ β”œβ”€β”€ clip_l.safetensors β”‚ β”‚ β”œβ”€β”€ clip_l_TEXT_detail_improved.safetensors β”‚ β”‚ β”œβ”€β”€ t5xxl_fp16.safetensors β”‚ β”‚ β”œβ”€β”€ t5xxl_fp8_scaled.safetensors β”‚ β”‚ β”œβ”€β”€ GGUF β”‚ β”‚ β”‚ β”œβ”€β”€ t5xxl_Q5_K_M.gguf β”‚ β”œβ”€β”€ clip_vision β”‚ β”‚ β”œβ”€β”€ sigclip_vision_patch14_384.safetensors β”‚ β”œβ”€β”€ unet β”‚ β”‚ β”œβ”€β”€ Canny β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-canny-dev-fp8.safetensors β”‚ β”‚ β”‚ β”œβ”€β”€ GGUF β”‚ β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-canny-dev-Q4_0.gguf β”‚ β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-canny-dev-Q5_0.gguf β”‚ β”‚ β”œβ”€β”€ Depth β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-depth-dev-fp8.safetensors β”‚ β”‚ β”‚ β”œβ”€β”€ GGUF β”‚ β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-depth-dev-Q4_0.gguf β”‚ β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-depth-dev-Q5_0.gguf β”‚ β”‚ β”œβ”€β”€ Dev β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-dev-fp8.safetensors β”‚ β”‚ β”‚ β”œβ”€β”€ GGUF β”‚ β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-dev-Q3_K_S.gguf β”‚ β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-dev-Q5_K_S.gguf β”‚ β”‚ β”œβ”€β”€ Fill β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-fill-dev-fp8.safetensors β”‚ β”‚ β”‚ β”œβ”€β”€ GGUF β”‚ β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-fill-dev-Q3_K_S.gguf β”‚ β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-fill-dev-Q5_K_S.gguf β”‚ β”‚ β”œβ”€β”€ Schnell β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-schnell-fp8.safetensors β”‚ β”‚ β”‚ β”œβ”€β”€ GGUF β”‚ β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-schnell-Q3_K_S.gguf β”‚ β”‚ β”‚ β”‚ β”œβ”€β”€ flux1-schnell-Q5_K_S.gguf β”‚ β”œβ”€β”€ vae β”‚ β”‚ β”œβ”€β”€ ae.safetensors
🎨 SDXL β”œβ”€β”€ SDXL β”‚ β”œβ”€β”€ checkpoints β”‚ β”‚ β”œβ”€β”€ Hyper3d.safetensors β”‚ β”‚ β”œβ”€β”€ sd_xl_base_1.0.safetensors β”‚ β”‚ β”œβ”€β”€ sdxl-6-real-dream.safetensors β”‚ β”œβ”€β”€ checkpoints_inpainting β”‚ β”‚ β”œβ”€β”€ Inpainting-Hyper3d.safetensors β”‚ β”œβ”€β”€ clip_vision β”‚ β”‚ β”œβ”€β”€ clip_vision_g.safetensors β”‚ β”œβ”€β”€ controlnet β”‚ β”‚ β”œβ”€β”€ xinsir-canny-sdxl-1.0.safetensors β”‚ β”‚ β”œβ”€β”€ xinsir-depth-sdxl-1.0.safetensors β”‚ β”‚ β”œβ”€β”€ xinsir-openpose-sdxl-1.0.safetensors β”‚ β”œβ”€β”€ vae β”‚ β”‚ β”œβ”€β”€ sdxl_vae.safetensors
🧠 ADetailer β”œβ”€β”€ Adetailer β”‚ β”œβ”€β”€ Ultralytics β”‚ β”‚ β”œβ”€β”€ bbox β”‚ β”‚ β”‚ β”œβ”€β”€ face_yolov8m.pt β”‚ β”‚ β”‚ β”œβ”€β”€ hand_yolov8s.pt β”‚ β”œβ”€β”€ sams β”‚ β”‚ β”œβ”€β”€ sam_vit_b_01ec64.pth
πŸ‘€ Face Restore β”œβ”€β”€ FaceRestore_Models β”‚ β”œβ”€β”€ GFPGANv1.4.pth β”‚ β”œβ”€β”€ codeformer.pth
πŸ“ˆ Upscale β”œβ”€β”€ Upscale_Models β”‚ β”œβ”€β”€ 4x-UltraSharp.pth β”‚ β”œβ”€β”€ RealESRGAN_x2plus.pth
--- ### πŸ‘οΈ I See You Downloads keep rising… but with zero new hearts or comments, I have no idea if I'm helping anyone or just feeding a download bot farm in silence. If this helped you out, leave a heart. Otherwise I’ll assume I built this for the void (and a very busy botnet). πŸ˜… --- ## New to ComfyUI or just want clean workflows? πŸ“Ί Watch a cool youtube video I made 😁 – [If You're Struggling With ComfyUI, Watch This First](https://youtu.be/mht9Bg6lCL8?feature=shared) Flux workflows: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/kBL3fpOjto0bIlG28R1AQ.png) Available on my Patreon (free, no paywall): πŸ‘‰ [🚨 Flux Level 1 and 2 Just Dropped – Free Workflow & Guide below ⬇️](https://www.patreon.com/posts/flux-level-1-and-131945103?utm_medium=clipboard_copy&utm_source=copyLink&utm_campaign=postshare_creator&utm_content=join_link) SDXL workflows: ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/PEbBMjf8ynE3WBejqUGZE.png) Available on my Patreon (free, no paywall): πŸ‘‰ [🚨 SDXL v1.5 Just Dropped β€” Free Workflows Below πŸ‘‡](https://www.patreon.com/posts/sdxl-v1-5-just-129782694?utm_medium=clipboard_copy&utm_source=copyLink&utm_campaign=postshare_creator&utm_content=join_link) --- ## Flux Showcase: ## 🧠 Depth: Flux Depth uses the depth map of an image, letting you prompt for what to fill it with. It's great for keeping the spatial layout while restyling the image however you want. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/YLE0jh0X3qO__vS4h1f-1.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/Hd0DOmPnTSqjCvfzABDoM.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/yFNCYv-08wut1K87fFv8V.png) ## ✏️ Canny: Flux Canny uses an edge map and also lets you prompt freely. It’s especially good for repurposing parts of an image like the planet in the first example. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/FV13PVe_l-uFERAeVfdWK.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/A2reIjbDkbBnikRa86mVV.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/0Fk1SQYdIyGlC0E-2HO1Z.png) ## πŸ•Ί OpenPose: Self-explanatory. It’s great when you don’t want Depth or Canny getting distracted by other elements in the original image. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/_9a1JRwBkdNn7-maidDjC.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/CUIgx3hEbclKMzVyVFXIb.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/W-WYDZQ_YvgPQhUq-hrt2.png) ## 🫠 Pulid Face Transfer Pulid lets you use a face as a reference and prompt as usual. The result will keep a rough match of the reference face. It’s pretty solid without needing any training, though not perfect. As you can see, it struggled with Aloy’s hair. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/XJT0orG8cA7i1rgFg_UuT.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/bqnrW1jSBWuimCUImh71S.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/t-UYkGTPrFNqPSC1N_fdJ.png) ## πŸ”„ Redux Use the style of one image along side your prompt to influence the result. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/garxHfPDqbarwGcIebVAo.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/-4kYoUTxcz0aN9fLEFS9E.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/67074acfd4d3da176ab29e70/UAVUwZ7oBppSwxVF-hq_c.png)