Troubleshooting Generations
Work from the simplest possible job: one prompt, one model, default settings, and no optional LoRAs or references. Change one thing at a time so you know what helped.
| What you see | What to check |
|---|---|
| Generate or Edit Image will not submit | Confirm that you are signed in, have available credit, and supplied all required inputs. Check any message shown beside the control. |
| A job is still processing | Check the tool's Results panel or mobile Results tab, then History. Avoid repeatedly submitting the same paid job while one is already running. |
| The result is unlike the prompt | Put the main subject first, remove conflicting styles, and describe visible details. Try Basic Prompting. |
| A reference barely changes the output | Check that it is active and that its reference type is supported by the selected model. For image-to-image, adjust the Creativity control in small increments. |
| An edit changes too much | State what should remain unchanged, use fewer simultaneous requests, and check the input image crop and order. See Magic Edit. |
| A LoRA does not appear or gives poor results | Select a LoRA for the current model family, confirm it is enabled, and try a lower weight. Select LoRAs through Add LoRA, not <lora:...> prompt text. |
| A video moves too much or too little | Describe one action and one camera move over the selected duration. Use a clear first frame. See Video Generation. |
For a reproducible comparison, keep a fixed seed, model, dimensions, and sampler while changing one prompt phrase. Different models and workflows can interpret the same seed differently. ComfyUI's KSampler reference explains the seed, steps, guidance, sampler, scheduler, and denoising controls used by many image workflows.
If a job fails, keep its link or ID, the tool and model you selected, the approximate time, and the error message. For account or billing problems, see the Payment FAQ or email tony@dopaminegirl.com. Do not send passwords or payment credentials.