Bad Generations?

We’ve implemented full Checkpoint Coverage which required a significant update to our Worker code, which manages GPU coordination. Additionally, we’ve upgraded both ComfyUI and our CUDA version, both of which impact how images are generated, potentially affecting the style and quality of outputs.

Since the release, we’ve tackled various issues, including generator stability and concerns over image quality. We’ve rolled out several fixes and optimizations to improve performance, but we’ve also identified that ineffective prompting plays a significant role in subpar results. To help users get the most out of these updates, we’ve refreshed our prompt guide with clear guidelines on crafting better prompts for higher-quality generations.

Check out the full Guide to Prompting, here, and find a quick cheat-sheet on common prompt issues, below!

Potential IssueSolution
Misspelled wordsCheck your prompt for misspelled words and typos which the Prompt Parser might not understand.
Unsupported characters, code, URLs (e.g. \n, +, </break>, https://www.civitai.com) Remove all non-standard characters, code, URLs, etc.
Redundant descriptive words, or conflicting descriptive wordsRepeating the same keywords does not necessarily improve results and may lead to distortions. Additionally, using conflicting tokens – such as “realistic” and “anime-style” together – can confuse the model and produce inconsistent results.
Very high weights (e.g. (apple:2.5)), or many weighted words in the same promptVery high weight values, or many weighted values, can cause severe artifacting and incoherent outputs.*
Inconsistent Emphasis use (e.g. ((apple))))) or [[[appleCheck that all parentheses and square-brackets are properly opened and closed. Do not mix this style of Emphasis with Weighted values.
Incorrect prompting style for the Model in use (e.g. Pony Syntax – score_9_up, score_8, being used with Flux)Make sure you’re using the correct prompting syntax for the Model ecosystem. SD1.5, Pony Diffusion, and Flux, all have distinct preferred methods of prompting.
Many LoRAs and EmbeddingsWhile not always the case, many LoRAs and Embeddings can conflict in unforeseen ways. Try generating without any Additional Resources, then add them one-by-one.
Generator Advanced Mode!If you’ve toggled Advanced Mode ON in the Generator Resource picker, be aware that you may be able to combine Resources which don’t work well together! Start small, add LoRAs one by one and test the outputs!

*Civitai employs the Automatic1111 Prompt Parsing syntax, which differs from ComfyUI’s approach. In Automatic1111, prompt weights are normalized, meaning the system takes the mean of all assigned weights and adjusts them to maintain balance. This ensures no single element of the prompt disproportionately influences the final image. This doesn’t mean you can go wild! High token weighting is one of the key contributors to bad generation results.

Support

If you’ve read the Prompting Guide and explored some of the options above, yet your generations still aren’t turning out right, please let us know. You can submit a Support Ticket via our Ticket Portal, or email [email protected].

Be sure to include Job IDs for the affected images. These can be copied to the clipboard from the hexagonal “i” icon on the Generator Image Queue;