Repository navigation
Add seed, negative prompt and sampling controls for local SDXL images - #443
Open
smshagor-dev wants to merge 12 commits into
Open
smshagor-dev wants to merge 12 commits into
smshagor-dev wants to merge 12 commits into
Conversation
Owner
Author
|
The three Rust checks stopped at the same formatting difference in |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Image generation currently uses fixed hardware-based sampling steps and gives people no way to specify a seed or negative prompt.
This change adds an Image settings disclosure to the chat composer for image requests. It accepts an optional integer seed, 1–50 sampling steps, and a negative prompt. The selected values are passed through the regular chat or Work chat view, the frontend API wrapper, the Tauri command and the pinned stable-diffusion.cpp CLI (
--seed,--steps,--negative-prompt). The same currently selected options are used when retrying an image, including CPU retry.Leaving seed and steps empty preserves the existing renderer defaults. Backend validation rejects invalid seed/step values and overly long negative prompts before creating an image artifact. The UI limits its fields and uses the existing theme variables in light and dark modes. The SDXL smoke example remains on defaults.
Rust tests cover defaults and invalid settings. Resolution, aspect ratio and saved per-artifact settings are still separate follow-up work; an existing image's Retry action currently uses the user's current image settings, not a snapshot of its original parameters. Real SDXL hardware inference also remains unverified. Part of #319. Merge only after platform and frontend checks are green.