Tag: #controlnet
-
Replicate Anything with ControlNet, IPAdapter, and Florence2 CLIP Encoder in ComfyUI.
Read This Post: Replicate Anything with ControlNet, IPAdapter, and Florence2 CLIP Encoder in ComfyUI.In this project, I used a custom SDXL checkpoint, ControlNet with DepthAnythingV2, IPAdapter with style transfer, and the Florence2 open-source vision model to replicate the original photo. By integrating these three methods, the final image aligns with the original in terms of style, depth map, and descriptive prompt. How It Works𝐂𝐨𝐧𝐭𝐫𝐨𝐥𝐍𝐞𝐭 𝐰𝐢𝐭𝐡 𝐃𝐞𝐩𝐭𝐡𝐀𝐧𝐲𝐭𝐡𝐢𝐧𝐠: This tool…
-
Interior Design Workflow with Depth ControlNet for FLUX 1-dev.
•
Read This Post: Interior Design Workflow with Depth ControlNet for FLUX 1-dev.The FLUX 1-dev Depth ControlNet provides structural guidance in the generative process based on a depth map extracted from a single image. This model enables the generation of photorealistic images with precise control over composition, ensuring that the original image’s structure is preserved while allowing for text-guided edits.
-
Interior Design Workflow with Flux + RunwayML.
•
Read This Post: Interior Design Workflow with Flux + RunwayML.Text-to-image with Flux1 dev NF4 in ComfyUI.Image-to-video with Runway GEN-3 Alpha Turbo.
-
Rhinoceros + Grasshopper + Stable Diffusion Workflow.
Read This Post: Rhinoceros + Grasshopper + Stable Diffusion Workflow.Parametric model was designed with Rhino+Grasshopper.Video was generated using custom Stable Diffusion Checkpoint with LoRa and ControlNet.
-
“Mirage: A Dance of Light and Shadows” Music and Arts Festival
•
Read This Post: “Mirage: A Dance of Light and Shadows” Music and Arts Festival -
Multiview AI characters for architectural visualizations with SDXL1.0 + CharTurnerBeta.
Read This Post: Multiview AI characters for architectural visualizations with SDXL1.0 + CharTurnerBeta.In this simple experiment, I used stable diffusion (SDXL1.0) together with CharTurnerBeta embeddings to create multiview AI generated assets which are visually consistent across different angles for use in architectural visualisations.