A Collection of Google Colab Notebooks for scripts & projects
| Notebook | Info |
|---|---|
 |
ComfyUI-LongCat for long Video Generation (Tested on the L4) |
|
ComfyUI-Ditto for video Editing (Tested on the L4) |
|
ComfyUI-Ovi for Text/Image to Video with Audio (Tested on the L4) |
|
ComfyUI - 1 to 3 Images to 1 Image with Qwen Image Edit 2509 |
|
ComfyUI - Img+Vid2Vid with Wan2.2 Animate (Tested on the L4) |
|
ComfyUI - Img+Vid2Vid with VACE Fun (Compute units Required) |
|
ComfyUI - Style and Subject-Driven Image Generation with Flux.1Dev-USO |
|
ComfyUI - Img2Img with Qwen + DiffSynth-Control-LoRA |
|
ComfyUI - Img2Img with Qwen + DiffSynth-ControlNet (Depth, Canny, Inpaint) (Compute units Required) |
|
ComfyUI - Img2Img with Qwen + InstantX-ControlNet-Union |
|
Video to Gif (basic) |
|
Lip Sync with LatentSync |
|
Animation with Animate-X |
|
TTS with ZonosTTS |
|
T2V & T2I with Wan2.1_T2V_1.3B (Compute units Required) |
|
T2V & T2I with Wan2_1_T2V_14B (Compute units Required) |
|
Image to Video with Wan2_1_I2V_14B-480P (Compute units Required) |
|
Frame Interpolation with RIFE |
|
Basic Image to Video with LTX-Video |
|
Text to Video with LTX-Video |
|
Two Images to Video with LTX-Video |
|
T2V & T2I with Wan2.1_T2V_1.3B |
|
T2V & T2I with Wan2.1_T2V_14B GGUF Models |
|
Image to Video with Wan2.1_I2V_14B-480p GGUF Models |
|
I2V with Wan2.1_I2V_14B-480p GGUF Models & LoRA |
|
Faster I2V with Wan2.1_I2V_14B-480p GGUF Models, LoRA & Teacache |
|
Hidream_fp8 for Text to Image Generation (Compute units Required) |
|
Hidream_GGUF_Q5 for Text to Image Generation |
|
FramePack_fp8 for Image to Video Generation (Compute units Required) |
|
Upscale Images & Videos with Flux Upscaler |
|
Use Prompts to Edit Images with In-Context Edit |
|
LTXV-0.9.7-13B_Distilled_GGUF_Q6 for Image to Video Generation |
|
Wan 2.1 VACE 14B & CausVid LoRA for faster Text to Video Generation |
|
Wan 2.1 VACE 14B & CausVid LoRA for faster Image to Video Generation |
|
Wan 2.1 VACE 14B & CausVid LoRA for Video to Video Generation |
|
Wan 2.1 VACE 14B & CausVid LoRA for Image to Image Pose Transfer (Experimental) |
|
Use Prompts to Edit Images with Flux.1 Kontext Dev |
|
Faster I2V with Wan2.1 using Causvid, Lightx2v & Fusionx LoRAs |
|
I2V with Wan2.2 using Lightx2v LoRA |
|
T2V with Wan2.2 using Lightx2v LoRA |
|
First-Last Frame to Video with Wan2.2 |
|
Audio-driven Portrait Animation with Sonic |
|
Audio-driven Animation with InfiniteTalk & MultiTalk (Compute units Required) |
|
Qwen-Image for Generating & Editing Images |
|
Qwen-Image-Edit 2509 for 1-3 Images to 1 Image |
|
Flux1 Kontext Dev with Mask Editor for Inpainting |
|
Improved Qwen-Image-Edit-2509 (with Mask Editor) |
|
Chroma1-HD for text to Image |
You can find more notebooks here
Some of the comfyUI workflows are modifications of Kijai's workflows which you can find here
If you find these notebooks helpful, you can support me here
I currently don't have the time to review pull requests. If you find any bugs or run into issues, please report them in the Issues section. Thanks!