feat: upgrade MiniMax default model to M3#4
Open
octo-patch wants to merge 3 commits into
Open
Conversation
Add OpenAICompatiblePromptExpander class that works with any OpenAI-compatible LLM API for prompt expansion. This enables users to choose from multiple cloud LLM providers (MiniMax, OpenAI, DeepSeek, etc.) instead of being limited to DashScope or local Qwen models. Key changes: - New OpenAICompatiblePromptExpander class in wan/utils/prompt_extend.py following the existing PromptExpander base class pattern - Auto-detects MiniMax vs generic OpenAI setup via environment variables (MINIMAX_API_KEY or OPENAI_API_KEY + OPENAI_BASE_URL) - Handles reasoning model output by stripping <think> blocks - Added openai dependency to requirements.txt - Updated README with documentation of available prompt expansion backends
- Update default model from MiniMax-M2.5 to MiniMax-M2.7 - Update docstrings and README to reference M2.7 - MiniMax-M2.7 is the latest flagship model with enhanced reasoning and coding capabilities
octo-patch
force-pushed
the
feature/add-minimax-provider
branch
from
095057a to
40c4bbc
Compare
octo-patch
changed the title
octo-patch
force-pushed
the
feature/add-minimax-provider
branch
from
2e91333 to
40c4bbc
Compare
- Update default model from MiniMax-M2.7 to MiniMax-M3 - Update docstring and inline references to reflect M3 - Update README backend description accordingly Co-Authored-By: Octopus <liyuan851277048@icloud.com>
octo-patch
changed the title
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Upgrade the OpenAI-compatible prompt expander to use MiniMax-M3 as the default model.
Changes
MiniMax-M2.7toMiniMax-M3inwan/utils/prompt_extend.pyREADME.mdso the MiniMax backend description references M3Why
MiniMax-M3 is the latest flagship model, offering a 512K context window, up to 128K output, and image input support — a cost-effective choice for prompt expansion.
Testing
OpenAICompatiblePromptExpanderdefault resolves toMiniMax-M3whenMINIMAX_API_KEYis setmodel_name(e.g.MiniMax-M2.7) to opt out