Comparing NovelAI GLM 4.6 vs Xialong speed
NovelAIDemo summary
The creator switches back to the older GLM 4.6 model to demonstrate the visible difference in generation latency and 'hitching' compared to the new Xialong model.
Step-by-step
- Select the GLM 4.6 model from the model selection menu
- Generate an image to observe the latency
- Compare the generation speed and 'hitching' against the Jialong model
Options
- Enable streaming to load parts of the image during generation instead of waiting for the full file
Watch out for
- GLM 4.6 exhibits more 'hitching' during the generation process compared to newer models
Tips
- Use the streaming setting to avoid waiting for the full image to dump at once
Highlights
“there is a I would say a reasonable speed up but between GLM and Jialong”
All demos from “Xialong Just Dropped!| Here's Everything New in Novel AI”
- 4:191:14Testing generation speed in NovelAI XialongThe user demonstrates the real-time generation speed of the Xialong model in NovelAI using a raw prompt about a cyclops guardian, noting its near-instantaneous start.NovelAI· Text to Image
- 5:330:46Comparing NovelAI GLM 4.6 vs Xialong speedCurrentThe creator switches back to the older GLM 4.6 model to demonstrate the visible difference in generation latency and 'hitching' compared to the new Xialong model.NovelAI· AI Image Generator
- 11:371:36Exploring Xialong model settings and samplersThe video shows the NovelAI interface for the Xialong model, highlighting the simplified preset options and the reduced number of available samplers.NovelAI· AI Image Generator
- Watch “Xialong Just Dropped!| Here's Everything New in Novel AI” →
AI Image Generator
1:180:20Using tag suggestions and prompt barThe video shows the NovelAI interface suggesting specific tags as the user types and demonstrates the prompt length bar filling up.NovelAI- 2:090:49Adjusting prompt weights with bracketsThe tutorial demonstrates using curly brackets to strengthen tags and square brackets to weaken them, showing the visual difference in the resulting image's hair texture.NovelAI
- 4:320:21Recovering prompts via drag and dropThe video shows how to recover the original prompt and seed settings by dragging a previously saved NovelAI image back into the web interface.NovelAI
0:430:58Generate images using the Quick Start Gallery in NovelAIThe user demonstrates how to select an existing image from the NovelAI gallery to automatically copy its prompts and settings for a new generation.ぷろもでAI研究所【生成AI解説】- 3:111:12Configuring V4.5 Full model and quality tagsThe demonstrator selects the 'V4.5 Full' model, applies quality tag presets, and adjusts manual settings like Steps and Prompt Guidance.ぷろもでAI研究所【生成AI解説】
- 7:051:32Using Negative Prompts and Undesired Content presetsThe video shows how to access the 'Undesired Content' field to add negative prompts and select presets to fix common AI artifacts like incorrect hand anatomy.ぷろもでAI研究所【生成AI解説】
16:321:12Using Question Mark Categories for AI CorrectionThe creator shows a specific technique using a question mark in category headers (e.g., 'Legs?') to provide the AI with negative constraints or specific corrections for common mistakes.RentyAi- 5:330:46Comparing NovelAI GLM 4.6 vs Xialong speedCurrentThe creator switches back to the older GLM 4.6 model to demonstrate the visible difference in generation latency and 'hitching' compared to the new Xialong model.RentyAi
- 11:371:36Exploring Xialong model settings and samplersThe video shows the NovelAI interface for the Xialong model, highlighting the simplified preset options and the reduced number of available samplers.RentyAi