Add Ideogram-4 diffusion model architecture support#5
Merged
Conversation
A quantized GGMLTensor is backed by packed uint8 storage, so weight.dtype returns torch.uint8. Models that do x.to(weight.dtype) before a linear (Ideogram-4, Gemma-4, Qwen3.5, CogVideo, some VAEs) cast activations to uint8, corrupting them and breaking F.linear on MPS, which requires floating-point inputs. GGMLTensor.dtype now returns bfloat16 for quantized tensors; F16/F32 and unquantized tensors keep their real storage dtype. A loader-set compute_dtype takes precedence. Dequant paths read storage via .data and are unaffected. Regression-tested loading WAN 2.2 I2V A14B Q8_0 (1095 tensors) on MPS.
ComfyUI core already ships Ideogram-4 (comfy/ldm/ideogram4/, model_detection.py, supported_models.py). This adds the GGUF detection layer so Ideogram-4 GGUF files load via UnetLoaderGGUF instead of failing with "Unknown model architecture!". - tools/convert.py: ModelIdeogram4, detected by the combination of embed_image_indicator.weight (the discriminator core uses), input_proj.weight and layers.0.attention.qkv.weight - loader.py: "ideogram4" added to IMG_ARCH_LIST No tensor remapping is needed (GGUF tensor names already match core) and the quants in circulation (BF16/Q8_0/IQ4_NL) are already supported.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
city96#455