<h1 id="pixart-sigma-900m:-enhanced-text-to-image-model-gj4yiszzp">PixArt Sigma 900M: Enhanced Text-to-Image Model</h1><h2 id="model-overview-vmhq4tp6t">Model Overview</h2>PixArt Sigma 900M is a text-to-image generation model based on the PixArt Sigma architecture. This version has been expanded to 900M parameters, up from the original 600M base model. Two distinct variants are available:<ol><li>PixArt Sigma 900M Base (Photorealistic)</li><li>PixArt Sigma 900M Anime</li></ol><h2 id="key-features-c12zlm6aw">Key Features</h2><ul><li>900M parameters (300M more than the base model)</li><li>Improved image generation quality</li></ul><h2 id="technical-details-rj4517ldm">Technical Details</h2><ul><li>Architecture: PixArt Sigma variant</li><li>Parameter Count: 900 million</li><li>Base Model: 600M PixArt Sigma</li></ul><h2 id="credits-p47fj6qjv">Credits</h2><ul><li>Original PixArt Sigma model by <a target="_blank" rel="ugc" href="https://pixart-alpha.github.io/PixArt-sigma-project/">PIXART-Σ (</a><a target="_blank" rel="ugc" href="http://pixart-alpha.github.io">pixart-alpha.github.io</a><a target="_blank" rel="ugc" href="https://pixart-alpha.github.io/PixArt-sigma-project/">)</a></li><li>Based on <a target="_blank" rel="ugc" href="https://huggingface.co/jimmycarter">jimmycarter (Jimmy Carter) (</a><a target="_blank" rel="ugc" href="http://huggingface.co">huggingface.co</a><a target="_blank" rel="ugc" href="https://huggingface.co/jimmycarter">)</a> adaptation of PixArt Sigma</li></ul><h2 id="comfyui-compatibility-p1lvuwjng">ComfyUI Compatibility</h2>To use this model in ComfyUI, a custom node is required as ComfyUI does not natively support this variant at the moment. The necessary custom node can be found at: <a target="_blank" rel="ugc" href="https://github.com/city96/ComfyUI_ExtraModels">https://github.com/city96/ComfyUI_ExtraModels</a><h2 id="required-components-xqklk7yuo">Required Components</h2><ol><li>T5 Model:<ul><li>Download from: <a target="_blank" rel="ugc" href="https://huggingface.co/PixArt-alpha/PixArt-Sigma-XL-2-1024-MS/tree/main/text_encoder">PixArt-alpha/PixArt-Sigma-XL-2-1024-MS at main (</a><a target="_blank" rel="ugc" href="http://huggingface.co">huggingface.co</a><a target="_blank" rel="ugc" href="https://huggingface.co/PixArt-alpha/PixArt-Sigma-XL-2-1024-MS/tree/main/text_encoder">)</a> on Hugging Face</li><li>Naming Convention: Ensure the T5 model files are named exactly as they appear in the repository</li><li>Important: Remove any prepended "text_encoder" from the filenames if present</li></ul></li></ol><h2 id="setup-instructions-gpg6l85v4">Setup Instructions</h2><ol><li>Download the T5 model from the Hugging Face repository linked above</li><li>Rename the T5 model files if necessary, removing any "text_encoder" prefix</li><li>Install the custom ComfyUI node from the GitHub repository</li><li>Place all model files in the appropriate directories as specified in the ComfyUI_ExtraModels documentation </li></ol>

900M PixArt Sigma

900mPixartSigma_base_trainingData.zip

900mPixartSigma_base.safetensors

base

anime

Model OverviewPixArt Sigma 900M is a text-to-image generation model based on the PixArt Sigma architecture. This version has been expanded to 900M parameters, up from the original 600M base model. Two distinct variants are available:PixArt Sigma 900M Base (Photorealistic)PixArt Sigma 900M AnimeKey Features900M parameters (300M more than the base model)Improved image generation qualityTechnical DetailsArchitecture: PixArt Sigma variantParameter Count: 900 millionBase Model: 600M PixArt SigmaCreditsOriginal PixArt Sigma model by PIXART-Σ (pixart-alpha.github.io)Based on jimmycarter (Jimmy Carter) (huggingface.co) adaptation of PixArt Sigma

Files with SHA256: 8e38bc33dc46924a967e1a698f9135aa1f029d2fc7078c715db35de5a6ce555b