feat!: switch default hub model to FLUX.2 klein 9B (Q5_K_M GGUF)#218
Open
TimPietruskyRunPod wants to merge 1 commit intomainfrom
Open
feat!: switch default hub model to FLUX.2 klein 9B (Q5_K_M GGUF)#218TimPietruskyRunPod wants to merge 1 commit intomainfrom
TimPietruskyRunPod wants to merge 1 commit intomainfrom
Conversation
BREAKING CHANGE: The default hub deployment now uses FLUX.2 klein 9B instead of FLUX.1-dev-fp8. Existing workflows using CheckpointLoaderSimple with flux1-dev-fp8.safetensors will not work with the new default image. Use the flux1-dev-fp8 image tag for backward compatibility. - Install ComfyUI-GGUF custom node in Dockerfile base stage - Add flux2-klein-9b model download block (GGUF + text encoder + VAE) - Change default MODEL_TYPE from flux1-dev-fp8 to flux2-klein-9b - Add docker-bake.hcl target and CI/CD workflow entries - Update hub config (description + 25GB container disk) - Add new workflow files for FLUX.2 klein 9B GGUF - Update documentation across README, hub README, and deployment guide - Add diffusion_models + text_encoders to extra_model_paths.yaml Closes #217
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
flux2-klein-9bbuild target across Dockerfile, docker-bake.hcl, and CI/CD workflowsBreaking Change (6.0.0)
The default hub image ships a different model. Existing workflows using
CheckpointLoaderSimplewithflux1-dev-fp8.safetensorswon't work on the new default image. Users can use theflux1-dev-fp8image tag for backward compatibility.Model Details
flux-2-klein-9b-Q5_K_M.ggufmodels/unet/qwen_3_8b_fp8mixed.safetensorsmodels/text_encoders/flux2-vae.safetensorsmodels/vae/Total VRAM: ~16 GB on 24 GB ADA GPUs (8 GB headroom)
Test plan
docker build --platform linux/amd64 --build-arg MODEL_TYPE=flux2-klein-9b --build-arg HUGGINGFACE_ACCESS_TOKEN=<token> -t test-flux2 .UnetLoaderGGUFtest_input.jsonflux1-dev-fp8target still builds correctlyCloses #217