peteromallet

QwenEdit InSubject is a LoRA fine-tune for QwenEdit that significantly improves its ability to preserve subjects while making edits to images. It works effectively with both single subjects and multiple subjects in the same image. While the base model can perform various image edits, it often loses important subject characteristics or distorts the main subjects during the editing process. This LoRA addresses these limitations to provide more accurate subject-preserving image editing. `Make an image of [subject description] in the same scene [new pose/action/details]` You can include "in the same scene" to preserve the original scene and background while modifying the subject's pose, clothing, or other details. For example: `Make an image of the horned woman in the same scene seated on a low pink ottoman, adjusting the buckle on one of her matching blue heels while her other leg is delicately crossed, wearing a blue and gold dress with a ruffled collar, red lips and freckles, the vibrant pink background still filling the frame behind her.` The model excels at: - Preserving subject identity and key characteristics during edits - Maintaining subject proportions and anatomical accuracy - Making targeted edits without affecting the main subject - Strong subject-aware prompt adherence The model may struggle with: - Complex multi-subject scenes where subject boundaries are unclear - Very dramatic lighting changes that fundamentally alter subject appearance - Edits that require significant subject pose or orientation changes The QwenEdit InSubject LoRA was trained on a curated dataset of high-quality image editing pairs that focus on subject preservation. You can find this data here. - Model: https://huggingface.co/peteromallet/Qwen-Image-Edit-InSubject - Dataset: https://huggingface.co/datasets/peteromallet/high-quality-midjouney-srefs

QwenEdit InStyle is a LoRA fine-tune for QwenEdit that significantly improves its ability to generate images based on a style reference. While the base model has style transfer capabilities, it often misses the nuances of styles and can transplant unwanted details from the input image. This LoRA addresses these limitations to provide more accurate style-based image generation. To get the best results, start your prompt with the phrase: For example: `Make an image in this style of a serene mountain landscape at sunset.` The model excels at: - Capturing subtle style nuances from reference images - Avoiding unwanted detail transplantation from source images - Generating coherent images that match the intended style - Strong prompt adherence The model may struggle with: - Extremely abstract or unconventional artistic styles - Very specific technical details that conflict with the reference style - Occasional anatomy issues The QwenEdit InStyle LoRA was trained on a curated dataset of high-quality Midjourney style references. This dataset focuses on diverse artistic styles and provides clean style-content separation for better training. You can find the public dataset used for training here: https://huggingface.co/datasets/peteromallet/high-quality-midjouney-srefs - Model: https://huggingface.co/peteromallet/Qwen-Image-Edit-InStyle - Dataset: https://huggingface.co/datasets/peteromallet/high-quality-midjouney-srefs

InScene and InScene Annotate are a pair of LoRA fine-tunes for QwenEdit that enhance its ability to generate images based on scene references. These models work together to provide flexible scene-based image generation with optional annotation support. Both models are currently in beta and will be improved significantly over time. InScene The main model that generates images based on scene composition and layout from a reference image. InScene is trained on pairs of different shots within the same scene, along with prompts describing the desired output. Its goal is to create entirely new shots within a scene while maintaining character consistency and scene coherence. InScene is intentionally biased towards creating completely new shots rather than minor edits. This design choice overcomes Qwen-Image-Edit's internal bias toward making small, conservative edits, enabling more dramatic scene transformations while preserving the characters and overall scene identity. InScene Annotate InScene Annotate is trained on images with green rectangles drawn over specific regions. The model learns to generate images showing the subject within that green rectangle area. Rather than simply zooming in precisely on the marked region, it's trained to flexibly interpret instructions to show what's inside that area - capturing the subject, context, and framing in a more natural, composed way rather than a strict crop. InScene and InScene Annotate are currently in beta. InScene To use the base InScene model, start your prompt with: For example: `Show a different image in the same scene of: a bustling city street at night.` 1. Draw a green rectangle over the subject or area of interest in your reference image 2. Describe what you want to focus on and how it should change For example: `Zoom in on the girl, make her turn to the side and laugh` A ready-to-use ComfyUI workflow is included in this repository: - workflow.json - Complete ComfyUI workflow with model links and setup instructions The workflow includes all necessary nodes and links to download the required models (base Qwen-Image-Edit model, VAE, text encoder, and Lightning LoRA). The models excel at: - Capturing scene composition and spatial layout from reference images - Maintaining consistent scene structure while varying content - Understanding spatial relationships between elements - Strong prompt adherence with scene-aware generation - (Annotate) Precise control using annotated references The models may struggle with: - Very complex multi-layered scenes with numerous elements - Extremely abstract or non-traditional scene compositions - Fine-grained details that conflict with the reference scene layout - Occasional depth perception issues The InScene and InScene Annotate LoRAs were trained on curated datasets focusing on scene composition and spatial relationships. InScene uses pairs of different shots within the same scene, while InScene Annotate uses annotated images with green rectangle markers. The training data will be released publicly when it's in a more stable state. - Model: https://huggingface.co/peteromallet/Qwen-Image-Edit-InScene

For best results, include a description of the beast like so: "shoggothy tentacled monster with yellow smiley face and many eyes"