transformers - ✅(Solved) Fix Failed test case `test_model_generate_images` for janus model [1 pull requests, 1 comments, 2 participants]

Q: Expected behavior

test case pass. Although I added patch ``` --- a/src/transformers/models/janus/modeling_janus.py +++ b/src/transformers/models/janus/modeling_janus.py @@ -1285,7 +1285,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin): input_ids, model_kwargs = self._expand_inputs_for_generation( input_ids=input_ids, attention_mask=attention_mask, - expand_size=generation_config.num_return_sequences, + expand_size=generation_config.num_return_sequences or 1, **model_kwargs, ) @@ -1315,7 +1315,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin): # batch_size should account for both conditional/unconditional input; hence multiplied by 2. batch_size=batch_size * 2, # we should have at least a cache len of seq_len + num_image_tokens. - max_cache_len=max(generation_config.max_length, num_image_tokens + seq_len), + max_cache_len=max(generation_config.max_length or 0, num_image_tokens + seq_len), model_kwargs=model_kwargs, ) ``` it still gets failed.

transformers2026-03-17 10:40:18

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

huggingface/transformers#44792•Fetched 2026-04-08 00:52:53

View on GitHub

Comments

Participants

Timeline

Reactions

Author

kaixuanliu

Participants

kaixuanliu

ydshieh

Timeline (top)

mentioned ×2subscribed ×2commented ×1cross-referenced ×1

Fix Action

Fix / Workaround

test case pass. Although I added patch

--- a/src/transformers/models/janus/modeling_janus.py
+++ b/src/transformers/models/janus/modeling_janus.py
@@ -1285,7 +1285,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
         input_ids, model_kwargs = self._expand_inputs_for_generation(
             input_ids=input_ids,
             attention_mask=attention_mask,
-            expand_size=generation_config.num_return_sequences,
+            expand_size=generation_config.num_return_sequences or 1,
             **model_kwargs,
         )

PR fix notes

PR #45044: fix bug for janus model image generation

Repository: huggingface/transformers
Author: kaixuanliu
State: closed | merged: True
Link: https://github.com/huggingface/transformers/pull/45044

Description (problem / solution / changelog)

Fix issue in https://github.com/huggingface/transformers/issues/44792. @zucchini-nlp @ydshieh pls help review, thx!

Changed files

src/transformers/models/janus/modeling_janus.py (modified, +13/-8)
src/transformers/models/janus/modular_janus.py (modified, +13/-8)
tests/models/janus/test_modeling_janus.py (modified, +9/-10)

Code Example

--- a/src/transformers/models/janus/modeling_janus.py
+++ b/src/transformers/models/janus/modeling_janus.py
@@ -1285,7 +1285,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
         input_ids, model_kwargs = self._expand_inputs_for_generation(
             input_ids=input_ids,
             attention_mask=attention_mask,
-            expand_size=generation_config.num_return_sequences,
+            expand_size=generation_config.num_return_sequences or 1,
             **model_kwargs,
         )

@@ -1315,7 +1315,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
                 # batch_size should account for both conditional/unconditional input; hence multiplied by 2.
                 batch_size=batch_size * 2,
                 # we should have at least a cache len of seq_len + num_image_tokens.
-                max_cache_len=max(generation_config.max_length, num_image_tokens + seq_len),
+                max_cache_len=max(generation_config.max_length or 0, num_image_tokens + seq_len),
                 model_kwargs=model_kwargs,
             )

RAW_BUFFERClick to expand / collapse

System Info

transformers version: 5.3.0.dev0
Platform: Linux-5.4.292-1.el8.elrepo.x86_64-x86_64-with-glibc2.35
Python version: 3.10.12
Huggingface_hub version: 1.7.1
Safetensors version: 0.5.3
Accelerate version: 1.12.0
Accelerate config: not found
DeepSpeed version: not installed
PyTorch version (accelerator?): 2.10.0+cu128 (CUDA)
Using distributed or parallel set-up in script?: <fill in>
Using GPU in script?: <fill in>
GPU type: NVIDIA A100 80GB PCIe

Who can help?

multimodal models: @zucchini-nlp

Information

The official example scripts
My own modified scripts

Tasks

An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
My own task or dataset (give details below)

Reproduction

git clone https://github.com/huggingface/transformers.git cd transformers pip install -e . export RUN_SLOW=1 pytest -rA tests/models/janus/test_modeling_janus.py::JanusIntegrationTest::test_model_generate_images

Expected behavior

test case pass. Although I added patch

--- a/src/transformers/models/janus/modeling_janus.py
+++ b/src/transformers/models/janus/modeling_janus.py
@@ -1285,7 +1285,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
         input_ids, model_kwargs = self._expand_inputs_for_generation(
             input_ids=input_ids,
             attention_mask=attention_mask,
-            expand_size=generation_config.num_return_sequences,
+            expand_size=generation_config.num_return_sequences or 1,
             **model_kwargs,
         )

@@ -1315,7 +1315,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
                 # batch_size should account for both conditional/unconditional input; hence multiplied by 2.
                 batch_size=batch_size * 2,
                 # we should have at least a cache len of seq_len + num_image_tokens.
-                max_cache_len=max(generation_config.max_length, num_image_tokens + seq_len),
+                max_cache_len=max(generation_config.max_length or 0, num_image_tokens + seq_len),
                 model_kwargs=model_kwargs,
             )

it still gets failed.

extent analysis

Fix Plan

To fix the issue, we need to adjust the max_cache_len calculation to handle cases where generation_config.max_length is None. We can do this by providing a default value when generation_config.max_length is None.

Code Changes

--- a/src/transformers/models/janus/modeling_janus.py
+++ b/src/transformers/models/janus/modeling_janus.py
@@ -1285,7 +1285,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
         input_ids, model_kwargs = self._expand_inputs_for_generation(
             input_ids=input_ids,
             attention_mask=attention_mask,
-            expand_size=generation_config.num_return_sequences,
+            expand_size=generation_config.num_return_sequences or 1,
             **model_kwargs,
         )

@@ -1315,7 +1315,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
                 # batch_size should account for both conditional/unconditional input; hence multiplied by 2.
                 batch_size=batch_size * 2,
-                max_cache_len=max(generation_config.max_length, num_image_tokens + seq_len),
+                max_cache_len=max(generation_config.max_length or 0, num_image_tokens + seq_len),
                 model_kwargs=model_kwargs,
             )

Should be changed to:

--- a/src/transformers/models/janus/modeling_janus.py
+++ b/src/transformers/models/janus/modeling_janus.py
@@ -1285,7 +1285,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
         input_ids, model_kwargs = self._expand_inputs_for_generation(
             input_ids=input_ids,
             attention_mask=attention_mask,
-            expand_size=generation_config.num_return_sequences,
+            expand_size=generation_config.num_return_sequences or 1,
             **model_kwargs,
         )

@@ -1315,7 +1315,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
                 # batch_size should account for both conditional/unconditional input; hence multiplied by 2.
                 batch_size=batch_size * 2,
-                max_cache_len=max(generation_config.max_length, num_image_tokens + seq_len),
+                max_cache_len=max(generation_config.max_length if generation_config.max_length is not None else 0, num_image_tokens + seq_len),
                 model_kwargs=model_kwargs,
             )

Verification

To verify the fix, run the test case again:

pytest -rA tests/models/janus/test_modeling_janus.py::JanusIntegrationTest::test_model_generate_images

If the test passes, the fix is successful.

Extra Tips

Make sure to handle None values for generation_config.max_length

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

FAQ

Expected behavior

test case pass. Although I added patch

--- a/src/transformers/models/janus/modeling_janus.py
+++ b/src/transformers/models/janus/modeling_janus.py
@@ -1285,7 +1285,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
         input_ids, model_kwargs = self._expand_inputs_for_generation(
             input_ids=input_ids,
             attention_mask=attention_mask,
-            expand_size=generation_config.num_return_sequences,
+            expand_size=generation_config.num_return_sequences or 1,
             **model_kwargs,
         )

@@ -1315,7 +1315,7 @@ class JanusForConditionalGeneration(JanusPreTrainedModel, GenerationMixin):
                 # batch_size should account for both conditional/unconditional input; hence multiplied by 2.
                 batch_size=batch_size * 2,
                 # we should have at least a cache len of seq_len + num_image_tokens.
-                max_cache_len=max(generation_config.max_length, num_image_tokens + seq_len),
+                max_cache_len=max(generation_config.max_length or 0, num_image_tokens + seq_len),
                 model_kwargs=model_kwargs,
             )

it still gets failed.

#api #ssr #installation #tensor shape #autograd error #memory optimization #batch processing #GPU compatibility #latency issue #model loading

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

transformers - ✅(Solved) Fix Failed test case `test_model_generate_images` for janus model [1 pull requests, 1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

PR fix notes

PR #45044: fix bug for janus model image generation

Description (problem / solution / changelog)

Changed files

Code Example

System Info

Who can help?

Information

Tasks

Reproduction

Expected behavior

extent analysis

Fix Plan

Code Changes

Verification

Extra Tips

FAQ

Expected behavior

Still need to ship something?

TRENDING

transformers - ✅(Solved) Fix Failed test case `test_model_generate_images` for janus model [1 pull requests, 1 comments, 2 participants]

Recommended Tools

GitHub issue graph ai analysis

Fix Action

Fix / Workaround

PR fix notes

PR #45044: fix bug for janus model image generation

Description (problem / solution / changelog)

Changed files

Code Example

System Info

Who can help?

Information

Tasks

Reproduction

Expected behavior

extent analysis

Fix Plan

Code Changes

Verification

Extra Tips

FAQ

Expected behavior

Still need to ship something?

RELATED_DISCOVERY

TRENDING